© 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. 68400
    Prev
    Next
    INDEX
    Explanations

    ="@+id/ in XML

    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
     männer
    -2.50
     kopf
    -2.45
     古风
    -2.39
    鉝
    -2.38
    продам
    -2.36
    明日は
    -2.31
     katze
    -2.30
     ſtate
    -2.27
    
    -2.17
     münchen
    -2.14
    POSITIVE LOGITS
     vorigen
    3.16
    .”
    2.73
    ?"
    2.69
     allgemeinen
    2.31
     ewigen
    2.30
    可不是
    2.22
    d
    2.16
    o
    2.11
    re
    2.05
     le
    2.05
    Activations Density 0.002%

    No Known Activations