© 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. 71971
    Prev
    Next
    INDEX
    Explanations

    javascript function browser app program script

    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
    lizes
    -1.35
    öffentlichungen
    -1.30
    ifies
    -1.17
     viejo
    -1.15
    Ꮨ
    -1.14
     rosto
    -1.14
    Mô
    -1.13
     suyo
    -1.13
    issants
    -1.13
     användas
    -1.13
    POSITIVE LOGITS
     either
    1.50
     if
    1.49
     Wartawan
    1.38
    ければ
    1.34
     tracción
    1.27
     frenos
    1.25
    if
    1.23
     them
    1.22
     algorithm
    1.19
     Zoltán
    1.19
    Activations Density 0.327%

    No Known Activations