© 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. 10-GEMMASCOPE-RES-131K
    7. 24051
    Prev
    Next
    INDEX
    Explanations

    main function with argc or stdin

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

    The neuron spikes on the C/C++ “argc” parameter token in function signatures.

    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
    …
    -3.09
    _
    -2.73
    {
    -2.61
    —
    -2.56
     ‘
    -2.47
     
    -2.42
     We
    -2.42
     {
    -2.38
    }
    -2.38
    <i>
    -2.33
    POSITIVE LOGITS
    寕
    3.66
    镦
    3.14
     剧照
    3.05
    䛗
    3.05
    螽
    3.00
     広場
    2.98
    鱨
    2.94
     間取り
    2.94
    Ꮉ
    2.89
     باسلام
    2.83
    Activations Density 0.003%

    No Known Activations