© 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. 58023
    Prev
    Next
    INDEX
    Explanations

    software Foundation

    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
    了一会儿
    -1.71
     "../../../
    -1.48
    悻
    -1.45
    摁
    -1.41
    有些不
    -1.41
     walmart
    -1.40
    却是
    -1.39
    蓠
    -1.39
     into
    -1.38
    plotlib
    -1.38
    POSITIVE LOGITS
     increases
    1.69
     increased
    1.62
    Fakta
    1.59
    Paket
    1.56
     or
    1.54
     decreases
    1.53
     substantial
    1.52
     furthering
    1.52
     those
    1.52
     this
    1.51
    Activations Density 0.145%

    No Known Activations