© 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. 41359
    Prev
    Next
    INDEX
    Explanations

    elaborate, ornate, lavish

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

    The neuron activates on words that describe something as intricate or highly detailed—especially forms of “elaborate” (and synonyms like “ornate”).

    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
     delightfully
    -2.50
    蠖
    -2.44
    
    -2.27
     magnific
    -2.25
     decidedly
    -2.23
     wonderfully
    -2.14
     soooo
    -2.13
     konkret
    -2.11
    鹪
    -2.06
     acht
    -2.05
    POSITIVE LOGITS
    ?’
    3.20
    ,“
    2.94
    ?”
    2.91
     plethora
    2.81
    ,’
    2.75
     Like
    2.67
     While
    2.67
     unrelenting
    2.66
    …”
    2.66
     intricate
    2.64
    Activations Density 0.002%

    No Known Activations