© 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. 127565
    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
    Not in Any Lists

    No Comments

    Negative Logits
    螣
    -2.61
    fordshire
    -2.56
    thodoxy
    -2.44
     tijdens
    -2.42
     THEM
    -2.39
     meestal
    -2.36
     consulte
    -2.34
    ificantly
    -2.33
    vereignty
    -2.33
    ’
    -2.27
    POSITIVE LOGITS
    There
    3.78
    They
    3.06
    Those
    2.89
     very
    2.88
     two
    2.88
    It
    2.78
    the
    2.75
     intricacies
    2.72
     three
    2.70
    Not
    2.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.