© 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. 15104
    Prev
    Next
    INDEX
    Explanations

    code getters

    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
    );
    -2.36
     will
    -2.06
    ");
    -2.02
    i
    -1.90
    k
    -1.84
    t
    -1.78
    های
    -1.76
     eight
    -1.73
     two
    -1.66
    メートル
    -1.65
    POSITIVE LOGITS
     AMAZING
    1.84
    感じで
    1.75
    谖
    1.73
     撮
    1.67
     methodologies
    1.66
    都想
    1.64
    Hmmm
    1.64
    딪
    1.63
     REALLY
    1.63
    皝
    1.62
    Activations Density 0.001%

    No Known Activations