© 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. 45352
    Prev
    Next
    INDEX
    Explanations

    entitlement, indifference, underwriting

    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
    '
    -2.81
    ⸰
    -2.63
    If
    -2.58
    蹋
    -2.55
    -
    -2.52
     umbro
    -2.38
    鬭
    -2.38
    There
    -2.31
    if
    -2.30
    It
    -2.28
    POSITIVE LOGITS
    
    2.83
    辚
    2.80
    
    2.75
    䊐
    2.75
    媗
    2.70
    
    2.64
    𓐍
    2.55
    ㌧
    2.55
    杙
    2.55
    辔
    2.53
    Activations Density 0.002%

    No Known Activations