© 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. 22-GEMMASCOPE-RES-131K
    7. 16592
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ִּ
    -1.57
    駅から
    -1.56
    ַּ
    -1.50
    ֵּ
    -1.48
    ּוֹ
    -1.48
    頜
    -1.30
    mathrm
    -1.27
     back
    -1.27
     бампер
    -1.23
     at
    -1.22
    POSITIVE LOGITS
     również
    1.91
    ׇ
    1.76
     ویتامین
    1.58
     également
    1.57
     сахара
    1.55
     déput
    1.49
    Pengertian
    1.44
     también
    1.38
     også
    1.35
     även
    1.32
    Activations Density 0.046%

    No Known Activations