© 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. 39958
    Prev
    Next
    INDEX
    Explanations

    words starting with G

    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
    for
    -3.09
     voor
    -2.72
    riezmann
    -2.70
    蛧
    -2.69
    t
    -2.66
    l
    -2.64
    lioma
    -2.61
    s
    -2.55
    most
    -2.52
     untuk
    -2.52
    POSITIVE LOGITS
    苙
    2.95
     &
    2.81
    揠
    2.66
    艄
    2.61
    蓐
    2.50
     шесть
    2.45
    ’
    2.44
     लेकिन
    2.44
     самая
    2.41
    
    2.41
    Activations Density 0.031%

    No Known Activations