© 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. 35747
    Prev
    Next
    INDEX
    Explanations

    Premier League football

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

    The neuron fires primarily on numeric tokens—percentages, index figures, years, and other number expressions.

    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
     uska
    -0.86
     Heizung
    -0.79
    Mat
    -0.79
    //{
    -0.78
    Aud
    -0.77
     to
    -0.77
    M
    -0.76
     тогда
    -0.75
    Ba
    -0.74
    </h2>
    -0.72
    POSITIVE LOGITS
    
    1.02
    ꟷ
    1.00
    âce
    0.94
     yesterday
    0.93
    öy
    0.93
    tasche
    0.90
     last
    0.89
     aceea
    0.89
     WeChat
    0.88
     executar
    0.87
    Activations Density 0.049%

    No Known Activations