© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216168
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    等於
    0.37
     Генера
    0.35
     IGF
    0.33
    审
    0.32
    argument
    0.31
     perempt
    0.31
    쩍
    0.31
     CGC
    0.30
     imprim
    0.30
    🩶
    0.30
    POSITIVE LOGITS
     diaspora
    0.32
    স্ফ
    0.30
    ாட்டு
    0.30
    ואה
    0.30
     fiori
    0.30
    ܡ
    0.30
     resid
    0.29
    众
    0.29
     Lotus
    0.29
     fancied
    0.29
    Activations Density 0.001%

    No Known Activations