© 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. 83886
    Prev
    Next
    INDEX
    Explanations

    time blocks or space

    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
     Terkait
    -1.50
    While
    -1.44
    There
    -1.39
     بیشتری
    -1.39
    明细
    -1.38
    allclose
    -1.36
    ionados
    -1.35
    Since
    -1.34
     tendremos
    -1.33
    Today
    -1.32
    POSITIVE LOGITS
     for
    3.33
     such
    2.61
     to
    2.42
     that
    1.73
     where
    1.70
     the
    1.66
     для
    1.63
     at
    1.62
     solchen
    1.48
     in
    1.48
    Activations Density 0.023%

    No Known Activations