© 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. 6793
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declaration

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

    The neuron fires on the key legal‐disclaimer terms used in “as is” warranty sections—words like WARRANTY, CONDITION, ANY, KIND—that signal a “no warranty of any kind” statement.

    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
    imat
    0.62
    ellite
    0.59
    roughs
    0.56
    札
    0.56
    escap
    0.55
    verz
    0.55
    ichen
    0.55
    iku
    0.55
    unders
    0.54
    adors
    0.54
    POSITIVE LOGITS
     whatsoever
    0.65
     Lavinia
    0.62
     (>
    0.57
     (`
    0.56
     (’
    0.54
    станции
    0.54
     (${
    0.54
     [`
    0.52
     [<
    0.52
    (`#
    0.52
    Activations Density 0.009%

    No Known Activations