© 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. 112475
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    ﮑ
    -2.16
    
    -2.06
    
    -2.03
    ᚻ
    -2.03
    騭
    -1.93
    knights
    -1.91
     integridad
    -1.91
    rshire
    -1.90
    🪤
    -1.89
    uniqlo
    -1.87
    POSITIVE LOGITS
    “
    2.78
    R
    2.50
    re
    2.36
    H
    2.31
    as
    2.14
    _
    2.13
    B
    2.13
    ’’
    2.13
    ra
    2.11
    D
    2.09
    Activations Density 0.053%

    No Known Activations