© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    digits followed by 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
    Negative Logits
     GOOD
    -1.51
     all
    -1.45
     ALL
    -1.41
     an
    -1.33
    न
    -1.30
     FROM
    -1.28
     R
    -1.28
    出来ました
    -1.26
     OF
    -1.25
     about
    -1.24
    POSITIVE LOGITS
     peli
    1.46
     ,‬
    1.45
     CAROLINA
    1.39
     amet
    1.36
     ネック
    1.36
    essment
    1.34
    Моя
    1.34
    神
    1.33
     publicación
    1.33
     mando
    1.32
    Activations Density 0.002%

    No Known Activations