© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101082
    Prev
    Next
    INDEX
    Explanations

    function followed by parenthesis

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

    the keyword "function" in programming code, especially in function declarations and definitions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the “function” keyword (i.e. function definitions) 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_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
     eszköz
    -1.60
    ﹠
    -1.55
     opnieuw
    -1.55
    chọn
    -1.54
    dây
    -1.54
     bloqueo
    -1.52
    🛖
    -1.52
     gimnasio
    -1.52
    衚
    -1.52
     mikina
    -1.51
    POSITIVE LOGITS
    </h3>
    2.38
    o
    2.02
    y
    1.95
    ian
    1.91
    g
    1.90
    ”
    1.90
    ...
    1.84
    el
    1.84
    e
    1.82
    k
    1.82
    Activations Density 0.011%

    No Known Activations