© 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. 45583
    Prev
    Next
    INDEX
    Explanations

    Disney and sports media

    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
     who
    -1.41
    ならでは
    -1.23
     protože
    -1.21
     Krise
    -1.20
    後で
    -1.18
     illustratie
    -1.17
    を作って
    -1.17
    ոյ
    -1.16
    떠
    -1.14
    senic
    -1.12
    POSITIVE LOGITS
    )　
    1.33
    ⭐
    1.18
    🙏
    1.17
     if
    1.16
    Ⅰ
    1.13
    </h2>
    1.05
    repository
    1.05
    zysty
    1.04
    想象
    1.02
     ikke
    1.02
    Activations Density 0.027%

    No Known Activations