© 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. 58267
    Prev
    Next
    INDEX
    Explanations

    Dancing with the Stars appearances

    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
    時々
    -1.67
    嘰
    -1.62
    有两
    -1.55
     outras
    -1.52
     建物
    -1.52
     baskılı
    -1.49
    却不
    -1.45
    横に
    -1.45
     ВЫ
    -1.45
    転車
    -1.45
    POSITIVE LOGITS
     to
    2.08
    </h2>
    1.81
     Only
    1.49
    ～～
    1.45
     You
    1.40
     Aérea
    1.38
     устанавли
    1.37
    antado
    1.37
     In
    1.36
    mación
    1.35
    Activations Density 0.011%

    No Known Activations