© 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. 12917
    Prev
    Next
    INDEX
    Explanations

    estar disponible

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

    The neuron fires on comma tokens (its highest activations always occur at “,”).

    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
     whereupon
    0.59
     whereby
    0.55
     които
    0.55
    fallback
    0.54
     insofar
    0.54
     guid
    0.52
    ീസ്
    0.52
    -/-
    0.52
     conduit
    0.51
     எனப்படும்
    0.51
    POSITIVE LOGITS
    Alumno
    0.75
     言っ
    0.74
    డింది
    0.71
     Bakın
    0.71
     Gramm
    0.71
     바로
    0.70
     ನಿಮ್ಮ
    0.70
     设计
    0.69
     こちら
    0.69
     မှာ
    0.68
    Activations Density 0.000%

    No Known Activations