© 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. 127576
    Prev
    Next
    INDEX
    Explanations

    HTML attribute access

    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
    Mereka
    -2.17
    鹩
    -1.95
     majest
    -1.90
     robuste
    -1.86
    UIControlState
    -1.84
    𓆉
    -1.76
    Setelah
    -1.74
     Mereka
    -1.74
     texte
    -1.74
    缤
    -1.73
    POSITIVE LOGITS
     to
    2.02
     hitherto
    1.84
     You
    1.73
     then
    1.72
     sorgfäl
    1.68
     geschickt
    1.66
     it
    1.63
     znacz
    1.59
     which
    1.57
     where
    1.57
    Activations Density 0.002%

    No Known Activations