© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119640
    Prev
    Next
    INDEX
    Explanations

    Japanese and English content

    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
    趼
    -3.17
    鋮
    -2.73
    狆
    -2.67
    柃
    -2.56
     liso
    -2.55
    Проце
    -2.53
    เกง
    -2.52
    喈
    -2.50
    ggiato
    -2.47
    ſſer
    -2.45
    POSITIVE LOGITS
    '
    2.94
    (
    2.89
     are
    2.73
     and
    2.66
    /
    2.48
     or
    2.36
     aparecen
    2.31
     was
    2.25
     стал
    2.25
    \
    2.23
    Activations Density 0.001%

    No Known Activations