© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102778
    Prev
    Next
    INDEX
    Explanations

    HTML/JS attributes and directives

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

    hyphens in HTML/CSS attribute names and code syntax (like "data-role", "data-", class names with hyphens).

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -2.11
     ‘’
    -1.92
    h
    -1.84
    瓩
    -1.83
    她
    -1.76
    ,
    -1.70
     –
    -1.69
    血压
    -1.66
    s
    -1.66
    re
    -1.65
    POSITIVE LOGITS
    dacia
    2.02
    ubernur
    1.98
    licópter
    1.95
     whoſe
    1.95
    鴣
    1.86
    Istorija
    1.82
    舠
    1.80
    ätigung
    1.80
    adır
    1.77
    祧
    1.77
    Activations Density 0.073%

    No Known Activations