© 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. 6743
    Prev
    Next
    INDEX
    Explanations

    proper nouns and country names

    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
    “
    -3.45
    你
    -2.72
    桄
    -2.69
    焿
    -2.61
    𖥧
    -2.50
     keper
    -2.45
    B
    -2.44
    »،
    -2.38
     diskusi
    -2.33
    ～
    -2.33
    POSITIVE LOGITS
    峮
    3.19
    贻
    2.88
    涐
    2.83
    鷙
    2.72
    霂
    2.56
    烔
    2.52
     หรือ
    2.48
     is
    2.44
    
    2.44
     irgende
    2.41
    Activations Density 0.059%

    No Known Activations