© 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. 8853
    Prev
    Next
    INDEX
    Explanations

    how to solve it

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

    The neuron selectively activates on numeric tokens representing decimal (floating‐point) values.

    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
    Scrim
    0.53
     =
    0.53
    ',\
    0.52
    <h2>
    0.51
    <h4>
    0.51
    <h5>
    0.49
    ך
    0.49
     לע
    0.49
    '=
    0.49
     লুকিয়ে
    0.49
    POSITIVE LOGITS
     naziv
    0.73
     трубо
    0.69
     integrado
    0.65
    доступ
    0.64
     таке
    0.63
     rifiuti
    0.61
    ካት
    0.61
    UTCTime
    0.59
     emprego
    0.59
     cytologic
    0.59
    Activations Density 0.000%

    No Known Activations