© 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. 22-GEMMASCOPE-RES-131K
    7. 72134
    Prev
    Next
    INDEX
    Explanations

    generators and async operations

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

    The neuron detects tokens associated with asynchronous or concurrency control and delay operations (e.g. yield, take, select, time.After, Promise, Task.FromResult, chrono::milliseconds).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     keramik
    -1.25
    ⡃
    -1.24
     selam
    -1.21
     kenal
    -1.20
     notizie
    -1.17
     powiedzieć
    -1.14
    ندگی
    -1.13
    וּ
    -1.13
     wybrać
    -1.11
     mawar
    -1.11
    POSITIVE LOGITS
     
    1.31
     but
    1.23
     didn
    1.15
    logna
    0.95
     until
    0.93
     ngon
    0.91
    楽曲
    0.91
    izarse
    0.91
     credibility
    0.90
     hábit
    0.90
    Activations Density 0.001%

    No Known Activations