© 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. 6663
    Prev
    Next
    INDEX
    Explanations

    ruby code snippets

    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
     در
    -1.28
     برای
    -1.25
    ativität
    -1.18
    \
    -1.15
     enorm
    -1.15
     also
    -1.11
    ',
    -1.05
    4
    -1.05
    ことから
    -1.05
    ",
    -1.04
    POSITIVE LOGITS
     variadas
    1.43
     buscas
    1.34
    . 
    1.29
     their
    1.29
     any
    1.28
    Declare
    1.25
    ÕES
    1.20
    Bagaimana
    1.19
    Jeśli
    1.18
    Organisator
    1.18
    Activations Density 0.452%

    No Known Activations