© 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. 15820
    Prev
    Next
    INDEX
    Explanations

    role to play in or ranging between

    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
    または
    -1.28
    Those
    -1.22
    Jawab
    -1.21
    或
    -1.20
    gheny
    -1.20
     with
    -1.19
    Istorija
    -1.18
     not
    -1.17
    Bety
    -1.17
    Pgina
    -1.15
    POSITIVE LOGITS
     they
    1.42
     They
    1.36
    вина
    1.23
    --;
    1.23
     you
    1.20
     ",";
    1.20
     Они
    1.20
     próxima
    1.19
    
    1.16
     próprias
    1.16
    Activations Density 0.162%

    No Known Activations