© 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. 98634
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and abbreviations

    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
    幛
    -2.59
    Ꮵ
    -2.59
    
    -2.53
     greatly
    -2.52
     शुर
    -2.45
     spurred
    -2.44
    蕯
    -2.44
     should
    -2.44
     promotes
    -2.39
    وضح
    -2.39
    POSITIVE LOGITS
    厹
    3.17
     unn
    2.42
     of
    2.41
     
    2.39
     нескольких
    2.36
    และ
    2.34
     impec
    2.30
      
    2.30
     elegant
    2.28
     неболь
    2.28
    Activations Density 0.030%

    No Known Activations