© 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. 72280
    Prev
    Next
    INDEX
    Explanations

    "Despite" statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     but
    -1.89
     instead
    -1.54
     that
    -1.50
    もありますが
    -1.41
     però
    -1.36
     then
    -1.34
     akár
    -1.33
     especially
    -1.33
     invece
    -1.32
     inoltre
    -1.29
    POSITIVE LOGITS
     still
    1.77
     vẫn
    1.63
     its
    1.56
    still
    1.52
    仍
    1.34
    还是很
    1.27
    很快就
    1.26
    秾
    1.23
    </tbody>
    1.22
     Webseiten
    1.19
    Activations Density 0.054%

    No Known Activations