© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14791
    Prev
    Next
    INDEX
    Explanations

    import and using statements

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on import statements—i.e. occurrences of the keyword “import” (and analogous module‐loading lines) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMPLEMENTATION
    -0.95
    #%%
    -0.92
    kva
    -0.91
    råd
    -0.90
    %%
    -0.89
     perca
    -0.88
    koda
    -0.87
    ofold
    -0.87
     BEAUT
    -0.86
    стій
    -0.86
    POSITIVE LOGITS
     بیشتر
    0.95
    ：“……”
    0.94
    monium
    0.91
    するのが
    0.84
    ดน
    0.82
    LYPH
    0.82
    pp
    0.79
    からない
    0.79
    among
    0.79
     be
    0.78
    Activations Density 0.004%

    No Known Activations