© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15752
    Prev
    Next
    INDEX
    Explanations

    below / 下 / 아래 / ниже /下記の

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

    This neuron detects numeric references expressed with decimal points (e.g. section or citation numbers like “645.3129” or “1108.5208”).

    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
     거기
    0.66
    ڨ
    0.64
    зне
    0.63
     activación
    0.63
    oulders
    0.61
    ậ
    0.61
     activating
    0.61
    блиоте
    0.61
     preamble
    0.61
     चैप्टर्स
    0.61
    POSITIVE LOGITS
     below
    0.64
    ](#
    0.62
    below
    0.62
    Below
    0.55
    ((
    0.54
    ซึ่ง
    0.54
     গুজব
    0.54
    下面
    0.54
     pero
    0.52
     abaixo
    0.51
    Activations Density 0.017%

    No Known Activations