© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14846
    Prev
    Next
    INDEX
    Explanations

    code, units, or specific contexts

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

    The neuron flags typical legal‐disclaimer terms (e.g. “warranty,” “any,” “kind,” “implied,” “merchantability,” etc.).

    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_24_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
    ﯼ
    0.87
     encontrar
    0.86
     данных
    0.85
    ]]->
    0.85
    ў
    0.81
     achar
    0.78
    bauer
    0.77
     всего
    0.77
    奋
    0.77
     Росси
    0.76
    POSITIVE LOGITS
    '
    0.94
    тері
    0.70
    OY
    0.69
     alkoh
    0.68
    ’
    0.68
    #$%
    0.66
     supervis
    0.65
    _
    0.65
     sarcasm
    0.64
    ري
    0.64
    Activations Density 0.002%

    No Known Activations