© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49825
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese sentence endings

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     صحت
    0.79
    ور
    0.78
    ()
    0.77
    точно
    0.73
     जवळ
    0.72
    ق
    0.71
     اقدامات
    0.70
    ocks
    0.70
    ajat
    0.70
    ्राफी
    0.70
    POSITIVE LOGITS
    д
    0.98
    د
    0.95
    i
    0.92
    t
    0.89
    begin
    0.84
    d
    0.82
    л
    0.79
    na
    0.78
     THE
    0.78
    j
    0.78
    Activations Density 0.001%

    No Known Activations