© 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. 34-GEMMASCOPE-RES-131K
    7. 93125
    Prev
    Next
    INDEX
    Explanations

    async/await and API calls

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

    The neuron fires on code identifiers and type names related to asynchronous operations—e.g. “Promise<…>,” “QueryRunner,” “ReadAsStringAsync,” “Async,” etc.—so it’s detecting async/await–style or asynchronous API calls.

    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
     often
    -1.17
     frequently
    -1.04
     rarely
    -0.94
     =
    -0.87
     occasionally
    -0.85
     oftentimes
    -0.84
     constitute
    -0.84
     często
    -0.83
     seldom
    -0.83
     sometimes
    -0.83
    POSITIVE LOGITS
    SaveChangesAsync
    1.18
     Promise
    1.00
    wait
    0.96
    await
    0.90
     promesas
    0.88
    Promise
    0.86
    ConfigureAwait
    0.85
    ToListAsync
    0.85
    schuhe
    0.85
    catch
    0.85
    Activations Density 0.010%

    No Known Activations