© 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. 22-GEMMASCOPE-RES-131K
    7. 66758
    Prev
    Next
    INDEX
    Explanations

    sports team rosters and rankings

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

    The neuron fires on section headers and labels in sports team roster tables (e.g. “Current squad,” “Squad for the…season,” “Goalkeepers”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.55
     only
    -1.33
     gradova
    -1.17
     hidratante
    -1.12
     first
    -1.11
     countless
    -1.07
     two
    -1.06
    satunya
    -1.04
     sindical
    -1.04
     three
    -1.03
    POSITIVE LOGITS
    змом
    1.18
     remplacer
    1.16
     также
    1.09
    眉头
    1.09
     delightfully
    1.05
     egli
    1.04
     estavam
    1.04
     mouvements
    1.03
     dispuestos
    1.02
    乜
    1.02
    Activations Density 0.021%

    No Known Activations