© 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. 83930
    Prev
    Next
    INDEX
    Explanations

    badge, shields, swatch

    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
     ceremonia
    -1.95
    梛
    -1.82
    縢
    -1.75
    錾
    -1.73
     撮っ
    -1.67
     新款
    -1.62
    actéristi
    -1.60
     клетки
    -1.59
     inauguración
    -1.58
    秾
    -1.56
    POSITIVE LOGITS
     Главная
    1.61
    除此之外
    1.57
     fortsatt
    1.56
    了一句
    1.56
     совме
    1.55
    赑
    1.54
     dubbio
    1.51
    就得
    1.50
     δεν
    1.50
    こちら
    1.50
    Activations Density 0.003%

    No Known Activations