© 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. 45373
    Prev
    Next
    INDEX
    Explanations

    parentheses, brackets, 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
    Not in Any Lists

    No Comments

    Negative Logits
    They
    -1.77
     вони
    -1.55
    他們
    -1.54
     them
    -1.52
    美国的
    -1.48
    Они
    -1.48
     it
    -1.47
     charité
    -1.47
     chúng
    -1.45
     présidenti
    -1.45
    POSITIVE LOGITS
     empiezan
    1.58
     comienzan
    1.58
    ()
    1.55
     standout
    1.45
    C
    1.45
    res
    1.42
    king
    1.41
    re
    1.32
     (
    1.31
     "
    1.31
    Activations Density 0.133%

    No Known Activations