© 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. 50261
    Prev
    Next
    INDEX
    Explanations

    tennis tournaments and players

    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
     пря
    -0.81
     Knapp
    -0.75
     Sonne
    -0.75
    ैं
    -0.74
    。）
    -0.73
    枉
    -0.72
    stagland
    -0.72
    난
    -0.71
     officio
    -0.71
    roppo
    -0.71
    POSITIVE LOGITS
    Melbourne
    0.96
     Melbourne
    0.93
    Australian
    0.81
     Australian
    0.78
     Fluffy
    0.76
     délicieux
    0.76
     Jang
    0.75
     Resolutions
    0.74
     Australia
    0.73
     rés
    0.73
    Activations Density 0.018%

    No Known Activations