© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76962
    Prev
    Next
    INDEX
    Explanations

    owners may

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

    lists after colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    etl
    0.56
    soph
    0.54
    a
    0.54
    imperial
    0.52
    predict
    0.49
    histor
    0.48
    crisis
    0.48
    enterprise
    0.48
    served
    0.48
    predicted
    0.47
    POSITIVE LOGITS
    铨
    0.52
     ボタン
    0.47
    èque
    0.46
    étique
    0.45
     বিস্তারিত
    0.45
     Sexuality
    0.45
    OfYear
    0.44
     чтения
    0.44
    μία
    0.44
    ತ್ಯ
    0.43
    Activations Density 0.002%

    No Known Activations