© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50282
    Prev
    Next
    INDEX
    Explanations

    java mouse and key events

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

    The neuron strongly activates on occurrences of “mouse” (e.g. in method names, listener calls, and event types) in Java code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Capa
    -0.80
    setOnAction
    -0.79
    isArray
    -0.75
     тро
    -0.73
    proj
    -0.72
    icha
    -0.70
    reach
    -0.70
    actions
    -0.70
    Praxis
    -0.69
     JER
    -0.69
    POSITIVE LOGITS
     java
    0.79
    mpä
    0.79
     Wholesale
    0.75
    thag
    0.73
    仕様
    0.70
     Calendar
    0.70
    fault
    0.69
    Dag
    0.69
    rasing
    0.68
    🔇
    0.68
    Activations Density 0.034%

    No Known Activations