© 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. 78790
    Prev
    Next
    INDEX
    Explanations

    **kwargs argument passing

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

    The neuron fires on the special Python function‐call/definition syntax tokens used for argument unpacking and default assignment—namely the “*”, “**”, and “=” markers around args/kwargs.

    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
    érations
    -0.73
     marine
    -0.73
     candles
    -0.73
     COMPOS
    -0.73
    海軍
    -0.72
     Germ
    -0.69
     naval
    -0.69
    üş
    -0.68
    cao
    -0.68
    ajah
    -0.67
    POSITIVE LOGITS
     kwargs
    2.64
    kwargs
    2.52
     keyword
    2.48
     kw
    2.09
     Keyword
    2.05
    kw
    1.99
    Keyword
    1.99
     arguments
    1.89
     args
    1.83
    keyword
    1.83
    Activations Density 0.055%

    No Known Activations