© 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. 83658
    Prev
    Next
    INDEX
    Explanations

    seen doing or in

    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
     that
    -2.77
     they
    -2.42
     what
    -2.19
     about
    -2.08
    ).
    -2.08
     each
    -2.06
     every
    -2.06
     our
    -2.00
     it
    -1.97
     those
    -1.95
    POSITIVE LOGITS
     夜景
    1.87
     betek
    1.80
     juf
    1.80
     eisen
    1.73
     aar
    1.73
     tille
    1.72
     spion
    1.72
     lefs
    1.70
     tirs
    1.69
     dortmund
    1.69
    Activations Density 0.024%

    No Known Activations