© 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. 185622
    Prev
    Next
    INDEX
    Explanations

    term

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

    tool via

    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
    Negative Logits
    禾
    0.48
    深圳
    0.45
    蟀
    0.45
    গেট
    0.44
    家庭
    0.43
     дизайн
    0.43
    椑
    0.43
    ലീസ്
    0.43
    濟
    0.42
    團隊
    0.42
    POSITIVE LOGITS
    pport
    0.58
    (!
    0.57
    ii
    0.56
    ственными
    0.56
     fakt
    0.55
    it
    0.54
    ff
    0.53
     enige
    0.53
    il
    0.52
    bei
    0.52
    Activations Density 0.001%

    No Known Activations