© 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. 85779
    Prev
    Next
    INDEX
    Explanations

    onclick event handlers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on programming identifiers and function or method names (e.g. JavaScript/Vue event handlers, function calls, and variable names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ardent
    -1.36
     to
    -1.35
     ihtiyac
    -1.32
     prestazioni
    -1.30
    calça
    -1.30
    荩
    -1.30
    k
    -1.29
     beschrieben
    -1.28
     Pokud
    -1.24
     crainte
    -1.24
    POSITIVE LOGITS
     our
    1.55
     otomatis
    1.53
     joyería
    1.52
    følge
    1.48
     last
    1.48
    anyakan
    1.46
     same
    1.45
     this
    1.41
    優雅
    1.37
    awarkan
    1.34
    Activations Density 0.016%

    No Known Activations