© 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. 57975
    Prev
    Next
    INDEX
    Explanations

    meeting notes and roles

    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
     através
    -1.70
     жидкости
    -1.63
     bardzo
    -1.39
    ottes
    -1.34
     to
    -1.32
    ώ
    -1.31
     =
    -1.28
     município
    -1.26
     demuestra
    -1.25
     Dimensiones
    -1.25
    POSITIVE LOGITS
     enceinte
    1.43
    購物
    1.26
     agricultura
    1.18
     bote
    1.11
     propose
    1.09
    问题的
    1.09
     歳
    1.08
     snippetHide
    1.06
     eventually
    1.05
    ֑
    1.05
    Activations Density 0.043%

    No Known Activations