© 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. 119364
    Prev
    Next
    INDEX
    Explanations

    points or season championships

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

    This neuron fires strongly on numeric tokens—especially years, counts, and other digits—as they appear in the structured summary of a sports season.

    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
     Aya
    -0.90
    Gb
    -0.81
    diğimiz
    -0.79
    绘制
    -0.78
    ILS
    -0.78
    
    -0.78
    вла
    -0.77
    rated
    -0.77
    第五
    -0.75
    reportWebVitals
    -0.75
    POSITIVE LOGITS
     points
    1.43
     season
    1.22
     Points
    1.13
    points
    1.06
    Points
    1.02
     Punkte
    0.97
     Season
    0.88
    season
    0.85
     POINTS
    0.85
    puntos
    0.84
    Activations Density 0.020%

    No Known Activations