© 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. 34-GEMMASCOPE-RES-131K
    7. 60531
    Prev
    Next
    INDEX
    Explanations

    sports phrases and terms

    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
     airst
    -0.87
     Olympian
    -0.86
    días
    -0.81
    coupons
    -0.80
    milestone
    -0.79
    routers
    -0.78
    🦃
    -0.77
    trails
    -0.76
    khó
    -0.75
    ARGV
    -0.75
    POSITIVE LOGITS
     guadag
    0.93
     pembuatan
    0.89
     situations
    0.83
     specialist
    0.82
     kü
    0.81
     pemeriksaan
    0.79
     presence
    0.78
     pemer
    0.76
    Viewed
    0.75
     Verbreitung
    0.75
    Activations Density 0.061%

    No Known Activations