© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38633
    Prev
    Next
    INDEX
    Explanations

    specialized code keywords and symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    -1.80
     και
    -1.73
     sabias
    -1.72
    他们的
    -1.67
     calça
    -1.66
    ه‌ای
    -1.65
    が必要です
    -1.64
     rebajas
    -1.64
     italianos
    -1.63
     pergunta
    -1.59
    POSITIVE LOGITS
     and
    2.47
     for
    2.22
     of
    2.08
     on
    1.79
     like
    1.78
     to
    1.75
     in
    1.73
    This
    1.69
    These
    1.67
     that
    1.64
    Activations Density 0.005%

    No Known Activations