© 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. 57488
    Prev
    Next
    INDEX
    Explanations

    burr, bur, briar beginnings

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

    The neuron activates on occurrences of the character sequence “bur” (i.e. words that begin with “bur”).

    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
    ஂ
    -2.47
     sacerdotes
    -2.47
    甞
    -2.22
    
    -2.14
    ઁ
    -2.09
    et
    -2.02
    ii
    -1.99
    as
    -1.92
    фом
    -1.92
    鬭
    -1.90
    POSITIVE LOGITS
    кой
    2.20
    逦
    2.06
    к
    2.05
     These
    1.97
        
    1.95
    та
    1.91
     YOUR
    1.88
    Some
    1.87
    1
    1.87
    lifford
    1.86
    Activations Density 0.006%

    No Known Activations