© 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. 14106
    Prev
    Next
    INDEX
    Explanations

    java event handling listeners

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

    The neuron activates on Java event‐handling terms—especially class or interface names ending in “Event” or “Listener.”

    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
     próprios
    -1.57
     also
    -1.54
     bezw
    -1.52
     tivi
    -1.51
     anúncios
    -1.51
     jezt
    -1.49
     gewi
    -1.48
     inox
    -1.48
     cartões
    -1.44
     wata
    -1.44
    POSITIVE LOGITS
    Still
    1.42
     JUST
    1.41
    At
    1.41
     großen
    1.40
    Mereka
    1.37
    lytes
    1.36
     verduras
    1.34
    Not
    1.33
    Almost
    1.33
    2
    1.32
    Activations Density 0.004%

    No Known Activations