© 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. 10-GEMMASCOPE-RES-131K
    7. 22813
    Prev
    Next
    INDEX
    Explanations

    dispatch calls

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

    The neuron fires on tokens related to scheduling or dispatching asynchronous tasks (e.g. dispatch_once, dispatch_async, dispatch_after, main queue, scheduler).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     numberWith
    -1.59
     entwickelte
    -1.53
     gekenn
    -1.51
     writeTo
    -1.50
     através
    -1.47
     paura
    -1.44
     schli
    -1.42
     seite
    -1.41
     sapore
    -1.41
     reloadData
    -1.39
    POSITIVE LOGITS
     it
    1.52
     get
    1.38
     not
    1.31
    สิ่ง
    1.30
     działania
    1.29
    kHz
    1.28
    山东
    1.28
     pieles
    1.27
    スタッフ
    1.26
    کتاب
    1.24
    Activations Density 0.013%

    No Known Activations