© 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. 15629
    Prev
    Next
    INDEX
    Explanations

    class and variable names

    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
    蕯
    -2.02
    鐃
    -1.98
    )
    -1.90
    銩
    -1.82
    Dzięki
    -1.79
    Bardzo
    -1.77
    咵
    -1.76
    Ubicación
    -1.75
    躝
    -1.74
     millon
    -1.70
    POSITIVE LOGITS
    鸶
    2.03
     he
    2.00
    ༀ
    1.89
    ৢ
    1.74
    ༷
    1.65
    蓥
    1.63
     Voraussetzung
    1.61
     sería
    1.55
    \
    1.53
    тися
    1.52
    Activations Density 0.015%

    No Known Activations