© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127928
    Prev
    Next
    INDEX
    Explanations

    This neuron detects asynchronous dispatch calls (e.g. dispatch_async/dispatch_get_main_queue patterns) in code snippets.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    Thank you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     podrán
    -1.06
    
    -1.05
     palav
    -1.05
     páss
    -1.05
    句話
    -1.04
     puede
    -1.03
     altre
    -1.02
    춰
    -1.02
    neurs
    -1.02
     brilh
    -1.02
    POSITIVE LOGITS
     local
    0.91
     меньше
    0.90
    日本で
    0.88
     verspre
    0.88
     centers
    0.88
    綜合報導
    0.87
    Према
    0.86
    racite
    0.86
    توضیحات
    0.85
     cristales
    0.85
    Activations Density 0.001%

    No Known Activations