© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68599
    Prev
    Next
    INDEX
    Explanations

    privately held, maintained, financed, communicated

    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
     to
    -2.63
     of
    -2.63
    '
    -2.36
     ซึ่ง
    -2.09
     \
    -2.09
     realizada
    -2.06
     We
    -2.05
     appreciably
    -2.02
    bandicam
    -1.99
     brasile
    -1.97
    POSITIVE LOGITS
    遢
    2.45
    welli
    2.06
    ."/
    2.05
    
    1.99
     almofada
    1.99
    himura
    1.97
     toalha
    1.96
    of
    1.95
    tures
    1.93
    ー
    1.92
    Activations Density 0.002%

    No Known Activations