© 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. 76287
    Prev
    Next
    INDEX
    Explanations

    Barkskin and additional names

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

    **`**` or punctuation

    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
     press
    0.49
     Midlands
    0.49
     Midland
    0.48
    igure
    0.47
     Henrietta
    0.46
     ছিলেন
    0.45
    %'
    0.45
     Crescent
    0.45
     she
    0.44
    [%
    0.44
    POSITIVE LOGITS
    நோய
    0.54
     permettent
    0.48
    நோய்
    0.48
     salaire
    0.47
     arbej
    0.47
    aszt
    0.45
    同时
    0.45
     soutenir
    0.45
     ذخ
    0.45
    тен
    0.44
    Activations Density 0.001%

    No Known Activations