© 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. 10-GEMMASCOPE-RES-131K
    4. 80661
    Prev
    Next
    INDEX
    Explanations

    sports championships and tournaments

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

    The neuron fires on numeric tokens—especially decimal or large numerical values—typically representing sports stats, championships, or tournament figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    :
    -1.16
     only
    -1.09
    ших
    -1.09
     of
    -1.09
     not
    -1.06
     variés
    -1.05
    ;
    -1.04
     lumpur
    -1.02
     paja
    -1.02
    国内
    -1.02
    POSITIVE LOGITS
     manuelle
    1.27
    ౦
    1.22
    ishes
    1.10
     穴
    1.10
     especialmente
    1.09
    Especially
    1.06
     primeiros
    1.05
     nosotros
    1.05
     nasz
    1.05
     RESOURCES
    1.04
    Activations Density 0.065%

    No Known Activations