© 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. 109519
    Prev
    Next
    INDEX
    Explanations

    competitions and tournaments

    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
     directos
    -0.90
    )։
    -0.88
    łaszcza
    -0.87
     procedente
    -0.84
    strata
    -0.82
     laf
    -0.79
    omsday
    -0.78
    рян
    -0.78
    getSystemService
    -0.78
    forhold
    -0.77
    POSITIVE LOGITS
     competitions
    3.34
     competition
    2.95
     tournaments
    2.77
    competition
    2.19
     events
    2.14
     tournament
    2.09
     Competitions
    2.08
    Competition
    2.03
     compétition
    1.83
    比賽
    1.81
    Activations Density 0.060%

    No Known Activations