© 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. 112990
    Prev
    Next
    INDEX
    Explanations

    Gustavo | USGS | osteoarthritis | Onyx | underscore

    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
    vantaged
    -3.30
    ⚣
    -3.11
    
    -3.05
    䛗
    -2.88
    茈
    -2.80
    魠
    -2.77
    蠖
    -2.73
    씰
    -2.70
    
    -2.67
    耷
    -2.64
    POSITIVE LOGITS
    ↵
    3.66
    ’
    2.72
     (‘
    2.55
    焄
    2.52
    During
    2.42
    t
    2.39
     There
    2.31
    ,’
    2.30
     ‘‘
    2.27
     ผม
    2.27
    Activations Density 0.003%

    No Known Activations