How to obtain the last convolucional layer of a visiontorch model?

I’m training an efficientnet b0 architecture on cifar 10. I want to apply grad cam in the last convolutional layer of this model. However i’m not sure about how to identify this layer and How to obtain It. Can you help me?

You could print the model and check what the last layer is or you could also check the model’s source code so see which layer is used last.