© 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. 22-GEMMASCOPE-RES-131K
    7. 16709
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     géographie
    -1.02
     ACKNOWLEDGMENTS
    -0.97
    أل
    -0.97
     Svet
    -0.88
     Pamph
    -0.88
    atural
    -0.88
    গ্র
    -0.88
    atissimo
    -0.88
     Ingo
    -0.86
    ناق
    -0.86
    POSITIVE LOGITS
    obrázek
    1.21
     podcast
    1.16
     biblioteca
    1.09
     parlant
    1.09
     célè
    1.04
     radio
    1.04
     kolik
    1.04
    Ширина
    1.04
     ständig
    1.03
    ardust
    1.02
    Activations Density 0.025%

    No Known Activations