© 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. 22889
    Prev
    Next
    INDEX
    Explanations

    new endeavors

    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
    !
    -1.32
    اری
    -1.31
     hond
    -1.30
     emballage
    -1.30
     solide
    -1.28
    --
    -1.27
     mirador
    -1.27
    龊
    -1.26
    стую
    -1.23
    &
    -1.20
    POSITIVE LOGITS
     such
    2.19
     takich
    1.63
     including
    1.56
    airplane
    1.54
     poszczegól
    1.52
     innymi
    1.50
     küche
    1.49
     innych
    1.45
     cuarent
    1.44
     eccellente
    1.44
    Activations Density 0.383%

    No Known Activations