© 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. 10-GEMMASCOPE-RES-131K
    7. 73853
    Prev
    Next
    INDEX
    Explanations

    function arguments

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

    The neuron specifically detects occurrences of the variable or parameter named “args” (i.e. code references to function arguments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     It
    -3.05
    酲
    -2.77
     them
    -2.67
    社会的
    -2.56
    玉石
    -2.44
    文化的
    -2.42
    鹩
    -2.38
    ”，
    -2.30
    ŚĆ
    -2.28
    傀
    -2.27
    POSITIVE LOGITS
    ↵↵
    3.23
    .,
    2.66
     justi
    2.47
    
    2.44
    筇
    2.41
    D
    2.38
    うれしい
    2.30
    鄣
    2.25
    b
    2.23
    \
    2.23
    Activations Density 0.004%

    No Known Activations