© 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. 68644
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    犼
    -2.91
    ophageal
    -2.83
    最后由
    -2.78
    们的
    -2.64
    the
    -2.63
    来不及
    -2.52
    洐
    -2.50
    泔
    -2.47
    互動
    -2.44
    逖
    -2.42
    POSITIVE LOGITS
     “
    2.55
     (‘
    2.44
    $
    2.41
            
    2.31
     pretende
    2.20
    ,’
    2.19
    ’
    2.17
    or
    2.11
    In
    2.09
    椟
    2.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.