© 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. 26878
    Prev
    Next
    INDEX
    Explanations

    rain and wind forecasts

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

    foreign languages and code

    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
     Пред
    0.42
     kết
    0.40
    詳
    0.40
    -
    0.40
    '
    0.40
    详情
    0.40
     Hiện
    0.40
     方
    0.40
     Frontend
    0.39
    лих
    0.39
    POSITIVE LOGITS
    ಓ
    0.45
    今日の
    0.42
     avem
    0.42
     “‘
    0.42
     outlandish
    0.41
    reading
    0.40
    樖
    0.40
    ಷ
    0.40
     meditations
    0.39
     realignment
    0.39
    Activations Density 0.038%

    No Known Activations