© 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. 38664
    Prev
    Next
    INDEX
    Explanations

    opto-electronic and Alison names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -4.38
      
    -3.09
     
    -2.77
     “
    -2.72
    <bos>
    -2.67
    ”,
    -2.58
     quintessential
    -2.55
    ’,
    -2.50
     cliché
    -2.44
    _{
    -2.42
    POSITIVE LOGITS
    盌
    2.88
    ﻒ
    2.72
    錞
    2.64
    
    2.56
     appareil
    2.56
    ſtanding
    2.53
    just
    2.52
    葙
    2.50
    when
    2.48
    دور
    2.47
    Activations Density 0.004%

    No Known Activations