© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76562
    Prev
    Next
    INDEX
    Explanations

    concurrency and asynchronous operations

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

    The neuron fires on code and text that involve multithreading or concurrency primitives—e.g. locks, thread constructs, and imports from concurrent‐related APIs.

    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
    secutive
    -0.83
     کد
    -0.81
     pursued
    -0.80
    QI
    -0.78
    oprop
    -0.75
    EDC
    -0.75
    pressor
    -0.75
    Santis
    -0.74
     Prelude
    -0.73
    deserialize
    -0.73
    POSITIVE LOGITS
     volatile
    0.96
    future
    0.89
     blocking
    0.88
    Future
    0.84
    volatile
    0.84
     Phaser
    0.79
     Blocking
    0.78
     Future
    0.77
    Blocking
    0.77
    executor
    0.75
    Activations Density 0.015%

    No Known Activations