© 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. 83766
    Prev
    Next
    INDEX
    Explanations

    binary and hex sequences

    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
     and
    -2.91
    ↵
    -2.61
     after
    -1.70
     In
    -1.69
     provide
    -1.54
     With
    -1.48
     .....
    -1.46
     &
    -1.45
     ....
    -1.41
     رغم
    -1.41
    POSITIVE LOGITS
     cérami
    2.02
    釤
    1.91
    鑁
    1.91
     Konkur
    1.84
     we
    1.82
    ಱ
    1.81
    ícias
    1.80
    偸
    1.79
    妧
    1.76
     kerk
    1.73
    Activations Density 0.003%

    No Known Activations