© 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. 107800
    Prev
    Next
    INDEX
    Explanations

    people playing professional sports

    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
    stadion
    -0.82
     SPORT
    -0.81
    titi
    -0.79
    mpl
    -0.78
     parámetros
    -0.78
    дцать
    -0.77
    thom
    -0.75
    aculture
    -0.75
    hubungan
    -0.75
     females
    -0.74
    POSITIVE LOGITS
     basketball
    1.80
     baseball
    1.40
     soccer
    1.39
     football
    1.37
     volleyball
    1.15
     tennis
    1.14
     Basketball
    1.02
     softball
    1.00
    basketball
    0.99
     hockey
    0.98
    Activations Density 0.077%

    No Known Activations