© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50481
    Prev
    Next
    INDEX
    Explanations

    UFC fights and fighters

    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
     shears
    -0.80
    ሱ
    -0.79
    Appellee
    -0.77
    kow
    -0.75
    iterraneo
    -0.74
    Ход
    -0.74
     caters
    -0.73
    čení
    -0.71
     Berto
    -0.71
     Appellants
    -0.71
    POSITIVE LOGITS
     健康
    0.85
    champ
    0.84
     title
    0.82
    Title
    0.79
     UFC
    0.79
    🏆
    0.78
     ママ
    0.78
     Title
    0.77
     defended
    0.77
     osu
    0.76
    Activations Density 0.019%

    No Known Activations