© 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. 45460
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    -1.59
     THAN
    -1.54
     чем
    -1.48
    ：……
    -1.48
    »,
    -1.45
     [
    -1.43
     nacht
    -1.40
     &
    -1.37
     ans
    -1.35
     моменты
    -1.35
    POSITIVE LOGITS
     that
    2.03
    0
    1.94
    er
    1.71
     Entdecken
    1.66
     gesuchten
    1.64
    Поэтому
    1.59
     Entfer
    1.56
     έχουν
    1.52
    姈
    1.52
     dată
    1.46
    Activations Density 0.010%

    No Known Activations