© 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. 38477
    Prev
    Next
    INDEX
    Explanations

    renderer

    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
     However
    -2.81
     That
    -2.69
     Virtually
    -2.63
    e
    -2.56
     But
    -2.56
     Our
    -2.47
     Before
    -2.45
     According
    -2.45
     So
    -2.42
     где
    -2.41
    POSITIVE LOGITS
    ᕱ
    2.72
    狴
    2.70
    ꞌ
    2.55
    盉
    2.52
     masque
    2.45
    alised
    2.41
     ܪ
    2.38
    塒
    2.38
     SEÑ
    2.34
     gewonnen
    2.28
    Activations Density 0.002%

    No Known Activations