© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28065
    Prev
    Next
    INDEX
    Explanations

    countries, epidemics, family, loans, numbers, centuries, steroids, musicians

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical or statistical information in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     OGSÅ
    -1.02
    auda
    -0.94
     пусть
    -0.94
     manguera
    -0.94
     doar
    -0.90
     zwy
    -0.89
    楽しみに
    -0.88
     traseira
    -0.88
     oś
    -0.88
    
    -0.88
    POSITIVE LOGITS
    你们
    0.96
     and
    0.96
    identité
    0.84
     or
    0.83
     :}
    0.82
     not
    0.82
    lijkheid
    0.82
    tanda
    0.81
    你們
    0.81
    madı
    0.79
    Activations Density 0.142%

    No Known Activations