© 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. 47277
    Prev
    Next
    INDEX
    Explanations

    belt or belts

    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
    мп
    -0.69
    phyllum
    -0.68
     muse
    -0.68
    LJ
    -0.68
    ıştı
    -0.67
    Bảo
    -0.67
    Proceed
    -0.67
    Pong
    -0.66
    istika
    -0.66
    stdio
    -0.66
    POSITIVE LOGITS
     belt
    5.50
     belts
    5.13
     Belt
    4.34
    belt
    4.31
    Belt
    4.03
     Belts
    3.77
    belts
    3.70
    ベルト
    3.31
     cinturón
    2.77
     ceinture
    2.66
    Activations Density 0.047%

    No Known Activations