© 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. 56734
    Prev
    Next
    INDEX
    Explanations

    Cardiff University and Journalism

    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
    ToScroll
    -0.86
    くり
    -0.78
     UIKit
    -0.76
     bancos
    -0.75
    anaf
    -0.75
    vábbi
    -0.69
    ミヤ
    -0.68
    ֤
    -0.68
     Punjab
    -0.68
     Lancashire
    -0.68
    POSITIVE LOGITS
     Cardiff
    1.96
    Cardiff
    1.79
     Bute
    1.06
     Nantes
    0.84
     capital
    0.82
     Glam
    0.81
     Cebu
    0.80
    ыре
    0.79
     Guangzhou
    0.78
    ODER
    0.78
    Activations Density 0.016%

    No Known Activations