© 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. 71547
    Prev
    Next
    INDEX
    Explanations

    job roles and places

    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
    縠
    -1.95
    大半
    -1.84
     comprehensively
    -1.79
    تیجه
    -1.77
     celebrated
    -1.76
    蒾
    -1.69
    .''
    -1.68
    芸
    -1.57
    畵
    -1.57
    
    -1.56
    POSITIVE LOGITS
    </strong>
    2.17
    ?’
    2.11
    
    1.96
    幸好
    1.86
    </sub>
    1.82
    スポンサーリンク
    1.80
    もともと
    1.78
    そういえば
    1.77
    ごめん
    1.73
    但他
    1.72
    Activations Density 0.015%

    No Known Activations