© 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. 72052
    Prev
    Next
    INDEX
    Explanations

    Tsar, Czar, Russian royalty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    苼
    -2.75
    麁
    -2.53
    搥
    -2.33
    乄
    -2.27
    桫
    -2.17
    蚡
    -2.16
    哙
    -2.08
    
    -2.06
     .......
    -2.05
     ホルダー
    -2.03
    POSITIVE LOGITS
    i
    2.45
    o
    2.44
    e
    2.44
    X
    2.11
    我也
    2.03
    N
    1.98
    just
    1.95
    猻
    1.91
    In
    1.91
    烱
    1.90
    Activations Density 0.005%

    No Known Activations