© 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. 22644
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     your
    -1.62
     is
    -1.52
     then
    -1.47
    </code>
    -1.44
    frac
    -1.36
     считает
    -1.34
     there
    -1.34
    self
    -1.31
    しっかり
    -1.30
     فهو
    -1.30
    POSITIVE LOGITS
    ;',
    1.41
     transparentes
    1.37
     permanentes
    1.37
    iczne
    1.32
    зык
    1.29
    ogues
    1.23
     pembunuhan
    1.23
     dever
    1.22
    льга
    1.21
     francès
    1.21
    Activations Density 0.202%

    No Known Activations