© 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. 38363
    Prev
    Next
    INDEX
    Explanations

    on event listeners and biological measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    references to user interface elements or programming callbacks like "OnItemSelected" and "OnKeyListener" in code.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    是我们
    -1.48
    了很多
    -1.45
    是非常
    -1.34
     procedente
    -1.34
     destinados
    -1.32
     meget
    -1.32
    来自于
    -1.32
     für
    -1.30
     permanece
    -1.30
    詳細は
    -1.29
    POSITIVE LOGITS
     of
    1.82
     kembali
    1.45
    THUR
    1.42
     golfe
    1.41
    也
    1.40
    ссу
    1.38
     Siria
    1.38
    ICING
    1.37
     Aggi
    1.34
    たちの
    1.32
    Activations Density 0.000%

    No Known Activations