© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130190
    Prev
    Next
    INDEX
    Explanations

    programming event handlers or listeners

    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
     Usually
    -1.78
    Usually
    -1.66
    ＠
    -1.57
     Despite
    -1.50
     Sometimes
    -1.45
     While
    -1.42
     Normally
    -1.41
    通常
    -1.41
     Peraturan
    -1.38
     Both
    -1.38
    POSITIVE LOGITS
     that
    2.70
     of
    2.14
     he
    2.02
    that
    1.48
     they
    1.46
    ズニー
    1.43
     този
    1.42
     семья
    1.34
     μεγά
    1.32
     vandens
    1.31
    Activations Density 0.004%

    No Known Activations