© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    ’s or 's

    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
    Not in Any Lists

    No Comments

    Negative Logits
     لیے
    -0.96
    不一样
    -0.93
    Также
    -0.90
     –>
    -0.90
     
    -0.87
     '[
    -0.87
     =)
    -0.87
     zimní
    -0.85
    本日は
    -0.84
    bentukan
    -0.84
    POSITIVE LOGITS
    
    0.95
     colorful
    0.94
    гом
    0.92
     https
    0.92
     Covid
    0.90
     ohne
    0.87
     blog
    0.87
     my
    0.87
     fifty
    0.87
     dictionnaire
    0.86
    Activations Density 0.057%

    No Known Activations