© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    JavaScript code and programming concepts

    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
     one
    -1.80
     about
    -1.78
    there
    -1.68
     There
    -1.65
     you
    -1.63
     situations
    -1.47
    詫
    -1.46
     of
    -1.42
     will
    -1.41
     many
    -1.41
    POSITIVE LOGITS
    และ
    1.93
    The
    1.87
    ܇
    1.80
     distinguer
    1.75
    ーーー
    1.67
    already
    1.65
     diriger
    1.62
    In
    1.58
    ーーーー
    1.55
     dévelo
    1.53
    Activations Density 0.008%

    No Known Activations