© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127600
    Prev
    Next
    INDEX
    Explanations

    weight and following context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    秾
    -2.61
     unquestion
    -2.45
     exacting
    -2.36
    habhar
    -2.31
    ↵↵
    -2.23
     outward
    -2.11
     δύο
    -2.09
     astonishing
    -2.09
     ferocious
    -2.08
     incredibly
    -2.06
    POSITIVE LOGITS
    ing
    5.00
    ة
    3.42
     untuk
    2.77
    an
    2.61
    ll
    2.61
    y
    2.56
    呓
    2.53
    荩
    2.38
    鉆
    2.33
    ၜ
    2.33
    Activations Density 0.003%

    No Known Activations