© 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. 34-GEMMASCOPE-RES-131K
    7. 79386
    Prev
    Next
    INDEX
    Explanations

    In a/an/the/its

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     this
    -1.18
    Şi
    -0.95
    дмила
    -0.94
    ASTER
    -0.91
    مين
    -0.90
    тились
    -0.89
     किसी
    -0.89
     ekst
    -0.88
     Karakter
    -0.88
    但这
    -0.88
    POSITIVE LOGITS
     a
    2.66
     its
    1.70
     an
    1.56
     another
    1.55
     statements
    1.54
     his
    1.52
     comments
    1.52
     separate
    1.44
     remarks
    1.35
     response
    1.28
    Activations Density 0.037%

    No Known Activations