© 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. 57051
    Prev
    Next
    INDEX
    Explanations

    preposition or verb followed by article/determiner

    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
    Not in Any Lists

    No Comments

    Negative Logits
     venerdì
    -1.49
     každý
    -1.43
    耵
    -1.42
    gewiesen
    -1.38
    ptian
    -1.38
     každého
    -1.36
     lunedì
    -1.35
    纐
    -1.31
    瘊
    -1.30
     všetkých
    -1.29
    POSITIVE LOGITS
     a
    5.91
     two
    3.55
     an
    3.47
     one
    3.16
     seorang
    3.13
    一个
    2.84
     một
    2.73
     एक
    2.63
     sebuah
    2.50
     someone
    2.44
    Activations Density 0.178%

    No Known Activations