© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28543
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese language context

    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/layer_31_width_65k_l0_medium
    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
    스
    0.49
    하시
    0.47
     trzeba
    0.46
    품
    0.44
    フォ
    0.44
    사
    0.43
     {
    0.43
     보면
    0.43
     by
    0.43
    한다
    0.42
    POSITIVE LOGITS
     dışında
    0.51
    lining
    0.50
    luğ
    0.49
    닿
    0.49
     ಹೇಗೆ
    0.49
     станет
    0.49
    й
    0.48
    ઠળ
    0.48
     becoming
    0.47
     nasıl
    0.47
    Activations Density 0.015%

    No Known Activations