© 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. 34-GEMMASCOPE-RES-131K
    7. 62555
    Prev
    Next
    INDEX
    Explanations

    category headings

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     this
    -1.23
     it
    -1.12
     only
    -1.05
     more
    -1.02
    หน้านี้
    -1.00
     especially
    -0.99
    iligt
    -0.96
     tasca
    -0.92
     even
    -0.91
     our
    -0.89
    POSITIVE LOGITS
     and
    1.52
     overview
    1.50
     &
    1.19
     jaka
    1.08
    </h2>
    1.05
     Overview
    1.04
     comparison
    0.99
    сятся
    0.96
     uphe
    0.95
    análisis
    0.94
    Activations Density 0.018%

    No Known Activations