© 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. 34-GEMMASCOPE-RES-131K
    7. 2991
    Prev
    Next
    INDEX
    Explanations

    `java.awt.event`

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

    The neuron identifies Java import lines, especially those pulling in the java.awt (and related javax) packages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Java code import/package statements, especially dot-separated package paths and related syntax.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    periods following Java package/class names in import statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     Antiquity
    -0.86
    Anxiety
    -0.82
    Negro
    -0.79
    ператор
    -0.79
     Anxiety
    -0.77
    ="";
    -0.77
    vimeo
    -0.77
    Terrain
    -0.76
    BROWN
    -0.76
     kvadrat
    -0.75
    POSITIVE LOGITS
     event
    1.17
    awt
    1.14
    event
    1.14
    Event
    1.13
     events
    1.04
    Overall
    0.97
     action
    0.96
     EVENT
    0.93
     Action
    0.92
    swing
    0.92
    Activations Density 0.004%

    No Known Activations