© 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. 102961
    Prev
    Next
    INDEX
    Explanations

    Olympic Committee and related bodies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numeric tokens (e.g. years, counts, IDs) wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     оформи
    -0.88
    Precalculus
    -0.79
    kelijk
    -0.75
     galería
    -0.73
    hütte
    -0.71
     endured
    -0.71
     desorption
    -0.70
     sinto
    -0.69
    不良
    -0.69
    ıkları
    -0.69
    POSITIVE LOGITS
     IOC
    1.92
    IOC
    1.48
     Olympic
    1.42
    Olympic
    1.04
     Olymp
    1.02
     olympic
    0.94
     Lausanne
    0.93
    ioc
    0.93
     Olympics
    0.88
    ッキー
    0.88
    Activations Density 0.027%

    No Known Activations