© 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. 22836
    Prev
    Next
    INDEX
    Explanations

    java package prefixes

    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
    Negative Logits
     That
    -2.44
     意思
    -2.41
     poté
    -2.33
    が無い
    -2.31
    を作る
    -2.28
    
    -2.19
    
    -2.14
    癰
    -2.14
     streamline
    -2.13
     universidades
    -2.13
    POSITIVE LOGITS
    ’
    3.17
    this
    2.86
     nî
    2.61
     itſelf
    2.55
    錵
    2.48
    寕
    2.44
     Gebruik
    2.41
    ~"
    2.39
     italia
    2.39
     手绘
    2.38
    Activations Density 0.003%

    No Known Activations