© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13664
    Prev
    Next
    INDEX
    Explanations

    winning championships and events

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

    The neuron responds to mentions of named sporting competitions or tournaments (e.g. “World Cup,” “NCAA Tournament,” “Olympics,” “championships”).

    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
     first
    -1.70
     at
    -1.45
     most
    -1.38
     currently
    -1.36
     from
    -1.23
     первую
    -1.23
     often
    -1.20
     occasionally
    -1.20
     jenem
    -1.20
     once
    -1.19
    POSITIVE LOGITS
     Bedürfnisse
    1.33
     Vainqueur
    1.19
    Instead
    1.19
    𓍊
    1.16
     事業
    1.16
    私は
    1.15
     Forderungen
    1.13
     tôi
    1.13
     decades
    1.13
     either
    1.13
    Activations Density 0.109%

    No Known Activations