© 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. 68506
    Prev
    Next
    INDEX
    Explanations

    punctuation before descriptive phrases

    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
     then
    -1.86
     muszą
    -1.63
    Пі
    -1.42
     Terbaik
    -1.41
     uitgenodigd
    -1.40
     zamiast
    -1.38
    ộm
    -1.37
     liggen
    -1.37
     потім
    -1.36
     vakantie
    -1.35
    POSITIVE LOGITS
     that
    1.95
     which
    1.91
     you
    1.66
      
    1.59
     also
    1.58
     because
    1.52
    ↵↵
    1.34
     également
    1.33
     tidigare
    1.28
     "
    1.26
    Activations Density 0.126%

    No Known Activations