© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20187
    Prev
    Next
    INDEX
    Explanations

    division and remainder

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

    The neuron fires on any mention of division—e.g. the slash operator or the words “divide,” “divided,” or “dividing.”

    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
    U
    -1.95
     المقبل
    -1.61
    1
    -1.54
    要点
    -1.41
     أصبح
    -1.41
    MMMM
    -1.41
    M
    -1.40
    S
    -1.37
     Теперь
    -1.36
     wasn
    -1.35
    POSITIVE LOGITS
     "
    2.05
     feroit
    1.85
    久しぶり
    1.74
     uwagi
    1.70
    歃
    1.70
    
    1.66
     起毛
    1.64
    ݮ
    1.63
    ￪
    1.62
     the
    1.59
    Activations Density 0.015%

    No Known Activations