© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12090
    Prev
    Next
    INDEX
    Explanations

    핵심, 주요, 기업, 사회, 산업

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

    The neuron detects Korean-language text (Hangul script).

    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
    但是
    1.16
    好像
    1.04
    所以
    1.03
    ؟
    0.99
    想
    0.99
    ؛
    0.99
    之间
    0.97
    喜欢
    0.97
    我的
    0.95
    写
    0.95
    POSITIVE LOGITS
     대표
    1.63
     기업
    1.60
     주요
    1.60
     핵심
    1.59
     연
    1.57
     각종
    1.57
     신
    1.55
     사회
    1.55
     다양한
    1.55
     공
    1.54
    Activations Density 0.008%

    No Known Activations