© 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. 128044
    Prev
    Next
    INDEX
    Explanations

    normalized measurements

    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
    黩
    -2.73
     The
    -2.66
     '
    -2.48
     októ
    -2.47
     rahasia
    -2.44
     škole
    -2.42
     ``
    -2.39
     naturels
    -2.39
    libat
    -2.34
     tejto
    -2.34
    POSITIVE LOGITS
    ↵
    3.53
    s
    3.05
    ‘
    2.80
    僰
    2.78
    J
    2.73
    要把
    2.69
    G
    2.66
    He
    2.66
    .’
    2.61
    
    2.56
    Activations Density 0.003%

    No Known Activations