© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3437
    Prev
    Next
    INDEX
    Explanations

    accessing variable assignments

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

    The neuron activates on programming identifiers—especially JavaScript module names, file paths, and related code tokens.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    []);
    0.69
    ₁(
    0.62
    。【
    0.61
    [][
    0.61
     кеңсесинде
    0.61
    ₂(
    0.60
    "]))
    0.56
    रखाव
    0.56
    образной
    0.56
    *)(
    0.55
    POSITIVE LOGITS
     =
    0.95
     from
    0.84
     —
    0.82
     $=
    0.73
     ="
    0.72
     $=$
    0.71
     ={
    0.70
     }=
    0.68
     ='
    0.64
     –
    0.63
    Activations Density 0.001%

    No Known Activations