© 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. 97608
    Prev
    Next
    INDEX
    Explanations

    GCC molded

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

    data processing and generation

    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
    N
    0.63
    Win
    0.51
    f
    0.51
    vision
    0.50
     Page
    0.50
    [
    0.50
     =
    0.48
    <em>
    0.48
    e
    0.48
    W
    0.47
    POSITIVE LOGITS
     patrimoine
    0.50
     ნაკ
    0.48
    瀵
    0.46
    儲
    0.46
     ಭಾರತ
    0.46
    سک
    0.45
     Франции
    0.45
    кість
    0.45
    парта
    0.45
    フランス
    0.44
    Activations Density 0.001%

    No Known Activations