© 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. 113933
    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
    er
    -1.51
    p
    -1.34
     compi
    -1.28
    庒
    -1.28
    if
    -1.21
     også
    -1.21
     will
    -1.20
     beni
    -1.18
     which
    -1.16
     tomat
    -1.13
    POSITIVE LOGITS
     sooo
    1.59
    despite
    1.50
     soooo
    1.48
    ſtre
    1.46
     והוא
    1.44
     čtyř
    1.44
    趼
    1.39
    nadequate
    1.38
    significantly
    1.38
    Cdt
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.