© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9468
    Prev
    Next
    INDEX
    Explanations

    人工智能, 苹果, 链接, 视频, 法律, 领域

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

    The neuron strongly activates on contiguous Chinese character sequences (i.e., segments of Chinese 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
     สมการ
    1.52
     Aussage
    1.49
     Mereka
    1.47
     }{}_{\
    1.45
     ไหร่
    1.37
     これらの
    1.33
     Quando
    1.32
     สูตร
    1.32
     Wanneer
    1.32
     ก่อน
    1.31
    POSITIVE LOGITS
    大
    1.29
    ,
    1.26
    等
    1.23
    在
    1.22
    (
    1.22
    新
    1.22
    一
    1.20
    本
    1.20
    就
    1.19
    自
    1.18
    Activations Density 0.000%

    No Known Activations