© 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. 50364
    Prev
    Next
    INDEX
    Explanations

    RxJS catchError or Q:

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

    The neuron fires on promise‐style chaining—i.e. it spots “.then(…)” calls in code.

    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
    longValue
    -0.84
    forEach
    -0.82
    law
    -0.76
    ា
    -0.76
     vedno
    -0.73
    utri
    -0.73
    rones
    -0.72
    цен
    -0.72
     pytest
    -0.71
    GroupBy
    -0.71
    POSITIVE LOGITS
    catchError
    0.93
     catch
    0.87
     retry
    0.81
     shared
    0.77
    ieee
    0.75
     necesaria
    0.75
    ≲
    0.75
     Shared
    0.75
    arro
    0.75
    вало
    0.75
    Activations Density 0.006%

    No Known Activations