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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57330
    Prev
    Next
    INDEX
    Explanations

    tennis tournament advancement

    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
     hiasan
    -1.00
     déficit
    -0.94
     picada
    -0.93
    Там
    -0.90
    ridas
    -0.89
     soyez
    -0.89
    řské
    -0.88
     Manusia
    -0.88
     Lebih
    -0.86
    engkapnya
    -0.85
    POSITIVE LOGITS
     tennis
    0.85
     next
    0.84
    ATP
    0.81
    </i>
    0.79
     Tennis
    0.78
    Tennis
    0.77
     متر
    0.74
     المح
    0.73
     onward
    0.73
    erc
    0.73
    Activations Density 0.000%

    No Known Activations