© 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. 71086
    Prev
    Next
    INDEX
    Explanations

    XML tags and numbers

    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
     that
    -2.09
     usually
    -1.90
     to
    -1.80
    .,
    -1.78
     you
    -1.75
    ,
    -1.74
    <>
    -1.70
    王爷
    -1.68
    >
    -1.67
    ),
    -1.63
    POSITIVE LOGITS
     bahkan
    2.08
    鲵
    2.03
    这个
    1.91
     maske
    1.91
    之后
    1.91
     حتی
    1.88
    
    1.86
     tenets
    1.84
     tehd
    1.83
     minne
    1.82
    Activations Density 0.003%

    No Known Activations