© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23237
    Prev
    Next
    INDEX
    Explanations

    조합, 단어, 모습

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

    Korean text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    東京
    0.93
    機種
    0.93
    様々な
    0.89
    約
    0.89
    年の
    0.88
    執行
    0.88
    年には
    0.88
    トヨタ
    0.88
    電池
    0.87
    今後
    0.87
    POSITIVE LOGITS
    에
    1.74
    은
    1.60
    의
    1.59
     단
    1.59
    을
    1.57
    보
    1.57
    로
    1.55
    인
    1.55
    할
    1.55
     테이블
    1.55
    Activations Density 0.012%

    No Known Activations