© 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. 83833
    Prev
    Next
    INDEX
    Explanations

    Commonwealth and European championships

    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
     Olympic
    -0.92
     based
    -0.77
     poorly
    -0.77
    オリンピック
    -0.71
    Sensory
    -0.71
    arischen
    -0.70
     Olímpicos
    -0.69
     Olympics
    -0.69
     ligiloj
    -0.69
     Zwe
    -0.67
    POSITIVE LOGITS
     Commonwealth
    2.06
    Commonwealth
    1.84
     commonwealth
    1.30
    England
    1.14
    Scottish
    1.00
     Glasgow
    0.97
    Australia
    0.91
    Melbourne
    0.87
    zzly
    0.86
    carro
    0.86
    Activations Density 0.038%

    No Known Activations