© 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. 18879
    Prev
    Next
    INDEX
    Explanations

    Mogollon, mojito, hogging, Gopalan, Noah

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

    zoom, Cream, GAMING

    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
    in
    0.90
    oS
    0.69
    innt
    0.67
    وين
    0.64
    리
    0.62
    inase
    0.61
    лог
    0.60
    看的
    0.60
    不喜欢
    0.60
    وفر
    0.59
    POSITIVE LOGITS
    <0x80>
    0.64
    ية
    0.63
     powied
    0.62
    mie
    0.61
    (
    0.60
    soever
    0.60
    ८
    0.60
    áme
    0.58
     по
    0.58
    하다
    0.58
    Activations Density 0.543%

    No Known Activations