© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139774
    Prev
    Next
    INDEX
    Explanations

    preferences coverage design

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

    economic differences

    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
    勇
    0.54
    鉉
    0.53
    Cô
    0.52
    龕
    0.52
    コラボ
    0.51
     collabor
    0.50
    헤
    0.49
    FORD
    0.49
    ллина
    0.49
    牒
    0.49
    POSITIVE LOGITS
    avelength
    0.45
     Sql
    0.44
     \
    0.43
    itzer
    0.43
    Default
    0.43
     Http
    0.42
     Tues
    0.42
     ?.
    0.42
     wavelength
    0.41
     sno
    0.41
    Activations Density 0.000%

    No Known Activations