© 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. 103895
    Prev
    Next
    INDEX
    Explanations

    sports competitions

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

    This neuron detects numeric statistics and figures—especially numerical data like counts, years, and performance metrics.

    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
    peč
    -0.81
    jav
    -0.79
     Characteristics
    -0.74
     characteristics
    -0.74
    liner
    -0.72
     support
    -0.70
    cox
    -0.70
     sumpay
    -0.70
    ofia
    -0.69
    selectedIndex
    -0.69
    POSITIVE LOGITS
     competitions
    2.58
     competition
    2.13
    Competition
    1.69
    competition
    1.67
     Competitions
    1.58
     COMPETITION
    1.52
     kompetisi
    1.45
     Competition
    1.43
     compé
    1.34
     compétition
    1.28
    Activations Density 0.039%

    No Known Activations