© 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. 127866
    Prev
    Next
    INDEX
    Explanations

    concentrating or pausing

    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
     OGSÅ
    -1.73
     you
    -1.51
     우리
    -1.43
     skvě
    -1.41
    低声
    -1.38
     obcí
    -1.36
     notamment
    -1.34
     você
    -1.34
     駅前
    -1.31
     fenô
    -1.30
    POSITIVE LOGITS
     had
    1.59
     began
    1.51
     his
    1.48
     was
    1.45
     seemed
    1.41
     by
    1.30
     remained
    1.29
     quickly
    1.28
     two
    1.24
     eager
    1.23
    Activations Density 0.033%

    No Known Activations