© 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. 22613
    Prev
    Next
    INDEX
    Explanations

    elapsed time units like century, year, week

    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
    ),
    -1.66
    ro
    -1.63
     as
    -1.63
    ”.
    -1.58
    ak
    -1.53
     had
    -1.52
    ra
    -1.49
     can
    -1.49
    !
    -1.48
     sees
    -1.48
    POSITIVE LOGITS
    ansı
    1.63
    甭
    1.61
    ühnen
    1.60
     sofrer
    1.58
     asisten
    1.57
     yere
    1.56
     Japão
    1.55
    嗬
    1.54
     Tonnen
    1.52
    絅
    1.48
    Activations Density 0.047%

    No Known Activations