© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11393
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron strongly activates on mentions of “import” (and closely related tokens like “from” when used in import/export contexts), i.e. references to importing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    んです
    0.62
    버
    0.60
    েনের
    0.59
     pilots
    0.58
    可以说是
    0.57
     ouvert
    0.57
    和你
    0.55
    呢
    0.55
    蝦
    0.55
    剞
    0.54
    POSITIVE LOGITS
     *
    1.11
     './
    0.84
     "*
    0.81
    ()*
    0.80
    .*
    0.74
     "./
    0.71
    (*
    0.70
    ('*
    0.70
    -*
    0.70
     *);
    0.70
    Activations Density 0.005%

    No Known Activations