© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70726
    Prev
    Next
    INDEX
    Explanations

    wedding events and celebrations

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

    The neuron fires on mentions of weddings or wedding‐related terms (e.g. “wedding,” “married,” “day”).

    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
     чор
    -1.23
     revel
    -1.20
     світу
    -1.20
     intuitively
    -1.19
     інші
    -1.19
     Paulista
    -1.17
    ctively
    -1.16
     поча
    -1.16
    ské
    -1.15
    ות
    -1.13
    POSITIVE LOGITS
    一个
    1.55
     также
    1.43
     that
    1.24
     another
    1.20
     rengi
    1.19
     cũng
    1.18
    También
    1.16
     kapturem
    1.16
     isang
    1.16
    有一个
    1.16
    Activations Density 0.024%

    No Known Activations