© 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. 22-GEMMASCOPE-RES-131K
    7. 32722
    Prev
    Next
    INDEX
    Explanations

    Rwanda, Kigali, Burundi

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     the
    -1.76
     our
    -1.50
    {
    -1.43
     such
    -1.42
     {
    -1.34
     a
    -1.24
     an
    -1.22
     desierto
    -1.16
     メニュー
    -1.15
     {\
    -1.14
    POSITIVE LOGITS
     especí
    1.28
    bmatrix
    1.20
     lidé
    1.17
     někdo
    1.16
     atributo
    1.15
    omino
    1.15
    igned
    1.15
     şi
    1.14
    ště
    1.13
    ophe
    1.13
    Activations Density 0.004%

    No Known Activations