© 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. 83861
    Prev
    Next
    INDEX
    Explanations

    Gladys Decker

    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
    e
    -4.78
    o
    -4.72
    t
    -3.53
    a
    -3.41
    h
    -3.02
    al
    -2.97
     bahwa
    -2.56
    m
    -2.53
    s
    -2.48
    d
    -2.47
    POSITIVE LOGITS
    咴
    2.97
    其妙
    2.94
    轳
    2.72
    橚
    2.56
     باسلام
    2.53
     soient
    2.50
    寕
    2.47
    嫱
    2.45
    啬
    2.41
    
    2.39
    Activations Density 0.004%

    No Known Activations