© 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. 22675
    Prev
    Next
    INDEX
    Explanations

    via a path or medium

    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
     of
    -1.88
    mathrm
    -1.55
     mantener
    -1.55
    во
    -1.41
    чи
    -1.39
    ⏑
    -1.36
     is
    -1.35
     chances
    -1.32
    -1.29
     content
    -1.28
    POSITIVE LOGITS
     вже
    1.71
     протягом
    1.66
    Reklama
    1.61
     кілька
    1.60
    鉿
    1.59
    Kako
    1.48
    錞
    1.48
    Аль
    1.47
    Андрей
    1.46
     потім
    1.45
    Activations Density 0.042%
    No Known Activations