© 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. 72268
    Prev
    Next
    INDEX
    Explanations

    usurped or muted states

    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
    
    -2.44
    銠
    -2.38
     現貨
    -2.36
    檍
    -2.34
     был
    -2.34
    龱
    -2.25
    】【
    -2.22
    愎
    -2.20
    癩
    -2.19
    銕
    -2.17
    POSITIVE LOGITS
    '
    2.52
     I
    2.42
     anderen
    2.38
     viele
    2.09
     diğer
    1.96
    偏偏
    1.87
     наиболее
    1.85
     cirka
    1.83
     بدأ
    1.81
    1.80
    Activations Density 0.001%

    No Known Activations