© 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. 114123
    Prev
    Next
    INDEX
    Explanations

    xhtml and code properties

    np_acts-logits-general · gemini-2.5-flash-lite

    whitespace and indentation in code or structured markup documents.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
     esmalte
    -1.99
     ventilador
    -1.87
     soldadura
    -1.80
    튿
    -1.80
     hormigón
    -1.79
     ་
    -1.74
    蕖
    -1.72
     repuesto
    -1.72
     vorige
    -1.66
     différents
    -1.65
    POSITIVE LOGITS
     with
    2.20
    In
    2.17
     in
    2.11
     to
    1.94
     по
    1.92
    in
    1.90
     on
    1.83
    After
    1.81
    on
    1.80
     на
    1.80
    Activations Density 0.008%

    No Known Activations