© 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. 113887
    Prev
    Next
    INDEX
    Explanations

    law and legal systems

    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
     unſ
    -1.77
    ,...
    -1.71
    鸶
    -1.66
    ization
    -1.63
    brtc
    -1.61
     («
    -1.61
     -"
    -1.58
    集群
    -1.57
    नलोड
    -1.54
    arraycopy
    -1.54
    POSITIVE LOGITS
    你
    1.86
     vorliegenden
    1.70
    してくれた
    1.70
     laws
    1.67
    لاب
    1.65
    也有
    1.62
     wiederhol
    1.62
    );
    1.60
     law
    1.57
     sportivo
    1.55
    Activations Density 0.013%

    No Known Activations