© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55668
    Prev
    Next
    INDEX
    Explanations

    async operations

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

    The neuron fires on async‐programming constructs—things like “async,” “await,” Task return types, and method names ending in “Async” (e.g. ReadAsStringAsync, EnsureSuccessStatusCode).

    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
    SaveChanges
    -0.79
     GONZ
    -0.75
    panic
    -0.74
    endus
    -0.72
    ToList
    -0.71
     bancaire
    -0.71
    公民
    -0.69
    流星
    -0.68
     MAINTENANCE
    -0.67
     pancre
    -0.67
    POSITIVE LOGITS
    Async
    2.69
    ContentAsync
    2.03
     async
    1.79
    RunAsync
    1.66
    ToListAsync
    1.64
     Async
    1.63
     ExecuteAsync
    1.62
    GetAsync
    1.56
    async
    1.53
    SaveChangesAsync
    1.51
    Activations Density 0.076%

    No Known Activations