© 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. 38346
    Prev
    Next
    INDEX
    Explanations

    rules of procedure

    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
    ’
    -1.66
     your
    -1.47
     them
    -1.34
    </h2>
    -1.30
      
    -1.27
    (
    -1.26
     be
    -1.25
    じゃなくて
    -1.25
     their
    -1.23
    ред
    -1.23
    POSITIVE LOGITS
    撂
    1.62
     ortam
    1.57
    䊐
    1.56
    闳
    1.56
     diejenigen
    1.52
    antMatchers
    1.50
    鳜
    1.49
    毆
    1.48
    бака
    1.48
    ranslated
    1.48
    Activations Density 0.015%

    No Known Activations