© 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. 72282
    Prev
    Next
    INDEX
    Explanations

    software version numbers

    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
    家が
    -1.86
     There
    -1.72
     terlebih
    -1.66
    sivos
    -1.66
    𝐭
    -1.65
     живут
    -1.63
     unwavering
    -1.63
    nemu
    -1.62
    ጴ
    -1.61
    𝗦
    -1.60
    POSITIVE LOGITS
    2
    2.44
    );
    2.02
     для
    1.88
    re
    1.87
     любой
    1.74
     version
    1.73
     was
    1.73
    in
    1.72
    originally
    1.66
    ↵
    1.63
    Activations Density 0.068%

    No Known Activations