© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129602
    Prev
    Next
    INDEX
    Explanations

    championship titles

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

    The neuron flags mentions of winning sports “titles” or “championships,” especially where they’re quantified by numbers.

    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
    </h3>
    -2.03
     thuy
    -1.78
     japoneses
    -1.73
    titial
    -1.71
    蹋
    -1.70
    艄
    -1.70
    étricas
    -1.63
     столько
    -1.57
     AMERIC
    -1.57
    ارتمان
    -1.55
    POSITIVE LOGITS
     sicheren
    2.16
     schnellen
    2.08
     Voraussetzung
    1.97
     Näch
    1.93
     erfolgreichen
    1.92
     ursprünglichen
    1.88
     вещей
    1.80
     individuellen
    1.80
     freundlichen
    1.80
     evidenced
    1.77
    Activations Density 0.016%

    No Known Activations