© 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. 34-GEMMASCOPE-RES-131K
    7. 55802
    Prev
    Next
    INDEX
    Explanations

    Swansea football club

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

    The neuron flags tokens that appear in a sports‐match preview header or schedule (team names, “vs,” venue names, date/time prepositions, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    姆
    -0.72
    caching
    -0.71
     remember
    -0.70
     помещения
    -0.69
     Rodriguez
    -0.69
    テト
    -0.69
    єр
    -0.68
     پ
    -0.66
    Variance
    -0.66
     rod
    -0.65
    POSITIVE LOGITS
     Asbury
    0.88
    ziem
    0.88
     Sima
    0.84
     originali
    0.80
     phosp
    0.79
    シカ
    0.79
    ANTES
    0.79
    Palo
    0.78
    tető
    0.77
    ättning
    0.77
    Activations Density 0.018%

    No Known Activations