© 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. 99479
    Prev
    Next
    INDEX
    Explanations

    angry birds

    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
     Denken
    -2.77
    ↵
    -2.73
     obwohl
    -2.47
    ’
    -2.42
    轳
    -2.41
    ݮ
    -2.38
    鲻
    -2.36
     goofy
    -2.33
    苤
    -2.33
     lauded
    -2.31
    POSITIVE LOGITS
     prado
    3.16
    s
    2.67
     jaj
    2.67
     emporio
    2.61
     Kelurahan
    2.48
     yzf
    2.48
     pajero
    2.47
     megane
    2.47
     jaja
    2.45
     hura
    2.45
    Activations Density 0.001%

    No Known Activations