© 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. 10-GEMMASCOPE-RES-131K
    7. 48099
    Prev
    Next
    INDEX
    Explanations

    sports figures and teams

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

    The neuron is strongly activated by proper names of sports teams, leagues, coaches, and star athletes.

    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
     now
    -1.76
     currently
    -1.66
     nyní
    -1.42
     obecnie
    -1.36
     vinilo
    -1.34
    currently
    -1.32
     lately
    -1.29
    当前
    -1.27
     actuels
    -1.23
    Actualmente
    -1.22
    POSITIVE LOGITS
     to
    1.35
     damals
    1.34
     then
    1.23
     тогда
    1.21
     entonces
    1.20
    ↵↵
    1.16
     champignons
    1.16
     dieną
    1.15
     mūsų
    1.14
     būtų
    1.13
    Activations Density 0.428%

    No Known Activations