© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13371
    Prev
    Next
    INDEX
    Explanations

    `@param` in documentation

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

    This neuron is activated by legal case citations (volume-reporter-page references).

    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
     जलदाय
    0.64
     качественно
    0.61
     SOUTH
    0.59
     southbound
    0.59
     pragmatic
    0.57
     GRAND
    0.56
     宋
    0.55
     réal
    0.54
     өчен
    0.54
     pinched
    0.54
    POSITIVE LOGITS
    var
    0.71
     jsx
    0.69
    Default
    0.60
    fontawesome
    0.57
    ECON
    0.56
    babel
    0.55
     var
    0.54
    ["
    0.54
    default
    0.54
    VAR
    0.54
    Activations Density 0.002%

    No Known Activations