© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2950
    Prev
    Next
    INDEX
    Explanations

    function argument documentation

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

    This neuron detects numeric constants—especially floating-point numbers (digits with decimal points) in the text.

    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_24_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
    面的
    0.74
    向け
    0.68
    غات
    0.64
    просы
    0.64
     بدور
    0.62
    ﺭ
    0.62
    わり
    0.61
    并没有
    0.61
    一下
    0.60
     오늘은
    0.60
    POSITIVE LOGITS
    ין
    0.73
     characterizes
    0.73
     authorizes
    0.71
    ма
    0.70
     параметр
    0.70
    ك
    0.68
    param
    0.67
     sağlar
    0.67
     integers
    0.64
     accessori
    0.64
    Activations Density 0.001%

    No Known Activations