© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67037
    Prev
    Next
    INDEX
    Explanations

    promise chaining in code

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

    The neuron strongly activates on JavaScript promise‐style chaining keywords and methods (e.g. “then,” “exec,” arrow callbacks), i.e. it detects promise‐chain operations.

    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
     for
    -1.01
    したので
    -0.94
     with
    -0.91
    žad
    -0.90
     after
    -0.89
     of
    -0.89
     on
    -0.88
    ース
    -0.85
    ın
    -0.84
     domés
    -0.84
    POSITIVE LOGITS
    Then
    1.00
     then
    0.97
    拿到
    0.91
    :^(
    0.90
     different
    0.88
     вдох
    0.87
     ARISING
    0.87
    ptăm
    0.87
     następnie
    0.87
     マスク
    0.86
    Activations Density 0.008%

    No Known Activations