© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3936
    Prev
    Next
    INDEX
    Explanations

    code constructs

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

    The main thing this neuron does is pick out programming‐style identifiers and code tokens (e.g. variable names, function calls, property accesses).

    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_24_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
    Η
    0.68
    @
    0.58
    Hola
    0.58
    А
    0.56
    Σ
    0.55
    Κ
    0.55
    Fem
    0.54
    Про
    0.53
     Під
    0.53
    Lady
    0.52
    POSITIVE LOGITS
     {};
    0.73
     '';
    0.71
     "";
    0.66
     [];
    0.61
     "]";
    0.59
     que
    0.55
     "'";
    0.50
     false
    0.48
    etään
    0.47
    =[];
    0.46
    Activations Density 0.000%

    No Known Activations