© 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. 6844
    Prev
    Next
    INDEX
    Explanations

    business and informational phrases

    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
    </td>
    -1.84
    あるので
    -1.80
    ”、“
    -1.61
    Leírás
    -1.58
     используя
    -1.52
    i
    -1.49
     sämtliche
    -1.44
     الكثير
    -1.42
     что
    -1.41
    Уважаемые
    -1.41
    POSITIVE LOGITS
     of
    1.62
     onderwijs
    1.57
    着一个
    1.52
     tieto
    1.48
    𝙞
    1.45
     in
    1.44
     подход
    1.39
     forskning
    1.38
    anneau
    1.38
     zostanie
    1.37
    Activations Density 0.002%

    No Known Activations