© 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. 22689
    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
    ire
    -0.95
    ८
    -0.93
    まさに
    -0.92
    つの
    -0.91
     ते
    -0.90
     From
    -0.90
    ти
    -0.88
    其中的
    -0.87
     heure
    -0.87
    Top
    -0.87
    POSITIVE LOGITS
     to
    1.23
     foglie
    1.13
     jsonArray
    1.06
    ikiran
    1.00
    لها
    0.97
    enuta
    0.93
     repertoire
    0.93
     society
    0.93
     nostre
    0.91
     sebelum
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.