© 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. 10-GEMMASCOPE-RES-131K
    7. 48343
    Prev
    Next
    INDEX
    Explanations

    Omega Speedmaster, association, score breakdown

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

    The neuron consistently activates on the Greek‐letter “Omega” symbol (Ω/Omega) appearing in the math text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ㍑
    -3.34
     壁纸
    -3.31
    ейчас
    -3.30
    旆
    -3.25
     westfalen
    -3.22
     広場
    -3.09
    Ᏹ
    -3.06
    眎
    -2.97
     باسلام
    -2.95
     插图
    -2.92
    POSITIVE LOGITS
    ↵↵
    4.19
    m
    3.17
     of
    2.98
     –
    2.92
     t
    2.92
    ?
    2.83
     not
    2.66
    呐
    2.61
      
    2.61
    ,
    2.59
    Activations Density 0.001%

    No Known Activations