© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    code variable 'i'

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

    The neuron detects decimal numeric literals (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ২০১৫
    0.60
    Owin
    0.60
    WebApi
    0.60
     ActionResult
    0.59
    DLL
    0.58
     "~/
    0.57
     DLL
    0.55
     ап
    0.55
     २०१
    0.55
     ২০১১
    0.54
    POSITIVE LOGITS
    TikTok
    0.71
    Biden
    0.71
     Biden
    0.71
     TikTok
    0.69
     nameof
    0.68
    🥳
    0.65
     Binance
    0.62
     Kherson
    0.62
    🤯
    0.62
    nameof
    0.61
    Activations Density 0.003%

    No Known Activations