© 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. 22809
    Prev
    Next
    INDEX
    Explanations

    German and Scandinavian names

    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
     comanda
    -1.72
     to
    -1.69
     him
    -1.56
    сед
    -1.52
     orale
    -1.48
    "}")
    -1.43
     terakhir
    -1.43
    zelfde
    -1.41
     retorn
    -1.41
     художе
    -1.39
    POSITIVE LOGITS
     国内
    1.58
    \
    1.58
     chút
    1.52
    Whom
    1.51
     سپاه
    1.48
    jaqueta
    1.47
    Hanya
    1.46
    Fernsehserie
    1.46
     搞笑
    1.44
    猜测
    1.43
    Activations Density 0.106%

    No Known Activations