© 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. 72241
    Prev
    Next
    INDEX
    Explanations

    boolean assertions or comparisons

    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
    ());
    -1.67
     acoged
    -1.51
     förslag
    -1.46
     toalla
    -1.44
     verksamhet
    -1.38
    كتور
    -1.38
    </em>
    -1.37
    ahora
    -1.35
    Penulis
    -1.34
    inerario
    -1.34
    POSITIVE LOGITS
     of
    1.38
    existent
    1.30
     
    1.27
    UNITIES
    1.24
    elded
    1.24
    vantaged
    1.20
     medan
    1.19
    DREN
    1.19
     mera
    1.19
    これに
    1.18
    Activations Density 0.019%

    No Known Activations