© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24063
    Prev
    Next
    INDEX
    Explanations

    Korean compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    шкой
    0.46
    還
    0.46
    廾
    0.46
    ᱚ
    0.45
    必ず
    0.45
    執行
    0.45
     campaigning
    0.45
    風格
    0.45
    純正
    0.44
    もう少し
    0.44
    POSITIVE LOGITS
    성
    0.70
    소
    0.62
    사
    0.60
    비
    0.59
    수
    0.58
    의
    0.57
     또는
    0.55
     수
    0.54
     및
    0.54
    스
    0.54
    Activations Density 0.001%

    No Known Activations