© 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. 22358
    Prev
    Next
    INDEX
    Explanations

    errors and misses

    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
    蚍
    -2.30
    ㍑
    -2.02
    ADORES
    -1.80
    蹀
    -1.80
    歘
    -1.74
    
    -1.73
    dann
    -1.73
     gants
    -1.71
    ㌘
    -1.71
    不得不说
    -1.70
    POSITIVE LOGITS
     of
    2.69
     at
    2.23
     on
    2.20
     also
    2.13
    as
    2.03
     for
    1.78
    and
    1.77
    ↵
    1.67
     with
    1.66
     m
    1.65
    Activations Density 0.003%

    No Known Activations