© 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. 58747
    Prev
    Next
    INDEX
    Explanations

    great + significant noun

    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
    erdings
    -1.86
    齜
    -1.72
    盦
    -1.69
    𐐀
    -1.64
    Ṅ
    -1.64
    实战
    -1.63
    entown
    -1.61
    fondos
    -1.61
    🧏
    -1.60
    躂
    -1.59
    POSITIVE LOGITS
     it
    1.89
     of
    1.87
     .
    1.77
    >
    1.71
     {
    1.64
     great
    1.60
    서는
    1.57
     up
    1.42
     
    1.40
     Although
    1.39
    Activations Density 0.048%

    No Known Activations