© 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. 22620
    Prev
    Next
    INDEX
    Explanations

    foreign languages and english 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     from
    -2.41
     and
    -2.03
     on
    -1.98
     we
    -1.95
     an
    -1.90
     until
    -1.88
     when
    -1.88
     These
    -1.84
     a
    -1.80
     because
    -1.66
    POSITIVE LOGITS
     usando
    1.82
    嵓
    1.78
     occuper
    1.70
     ‌
    1.65
     lâng
    1.64
     tecnológicos
    1.62
    臯
    1.61
     unbelievably
    1.60
    骉
    1.60
    罍
    1.59
    Activations Density 0.033%

    No Known Activations