© 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. 127611
    Prev
    Next
    INDEX
    Explanations

    collectible, collectives, collections

    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
     curtail
    -2.89
    t
    -2.83
    ↵↵
    -2.42
    </i>
    -2.34
    b
    -2.28
    を感じる
    -2.20
     optimise
    -2.19
    翆
    -2.14
     vielen
    -2.13
     zahlreichen
    -2.13
    POSITIVE LOGITS
    킁
    3.02
    ,:
    2.95
    읭
    2.91
    ﱠ
    2.75
    岽
    2.69
     Wartawan
    2.56
    
    2.55
     και
    2.53
    ?}
    2.52
    
    2.52
    Activations Density 0.003%

    No Known Activations