© 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. 45538
    Prev
    Next
    INDEX
    Explanations

    Event details, Home, Writers

    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
    来讲
    -1.56
    了两
    -1.38
     use
    -1.30
     you
    -1.30
     method
    -1.29
     السياس
    -1.27
     правительства
    -1.27
     Figuren
    -1.26
     service
    -1.21
     research
    -1.20
    POSITIVE LOGITS
     aceitar
    1.28
     mesmas
    1.27
     avaliar
    1.27
     esigen
    1.23
     lembrar
    1.19
    Aujourd
    1.19
     好看
    1.14
     apresentar
    1.14
     Configura
    1.13
     nyní
    1.13
    Activations Density 0.124%

    No Known Activations