© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6496
    Prev
    Next
    INDEX
    Explanations

    Japanese culture and haiku

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     multilingual
    0.46
    餃
    0.45
    tableView
    0.45
     Sichuan
    0.43
    姪
    0.42
    Chinese
    0.41
     communist
    0.41
    ☭
    0.41
     feminine
    0.41
    femin
    0.41
    POSITIVE LOGITS
     Bakufu
    0.45
     sushi
    0.44
    Sushi
    0.44
     Tokugawa
    0.43
     Japon
    0.41
     Field
    0.40
     일본
    0.40
     Sushi
    0.39
    学术
    0.39
     Цуки
    0.39
    Activations Density 0.109%

    No Known Activations