© 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. 34-GEMMASCOPE-RES-131K
    7. 32792
    Prev
    Next
    INDEX
    Explanations

    scheduling async tasks

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

    This neuron fires on the token sequence “runInEdtAndWait,” i.e. calls that schedule work on IntelliJ’s event-dispatch (EDT) thread.

    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
    unding
    -0.85
    Hard
    -0.84
    orsing
    -0.80
     mapStateToProps
    -0.78
     wist
    -0.77
    不清
    -0.77
     Hard
    -0.77
    Altro
    -0.75
    \!\
    -0.74
    kuwa
    -0.73
    POSITIVE LOGITS
    runOnUiThread
    2.39
     delayed
    1.36
    DispatchQueue
    1.35
     later
    1.27
    invokeLater
    1.23
     runnable
    1.23
     post
    1.22
     setTimeout
    1.20
    runOn
    1.20
    EventQueue
    1.20
    Activations Density 0.021%

    No Known Activations