© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68726
    Prev
    Next
    INDEX
    Explanations

    foreign words or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     this
    -1.46
    跸
    -1.43
    榊
    -1.34
    袿
    -1.34
     سایر
    -1.32
    澁
    -1.31
     Enix
    -1.28
     عبارت
    -1.27
     чемпи
    -1.22
     that
    -1.20
    POSITIVE LOGITS
    他们
    1.48
    ३
    1.30
    เคย
    1.30
    Cuando
    1.21
    ถ้า
    1.21
    以前
    1.17
    เมื่อ
    1.16
    如果
    1.15
    不断
    1.13
    昨天
    1.11
    Activations Density 0.055%

    No Known Activations