© 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. 42248
    Prev
    Next
    INDEX
    Explanations

    words starting with "Bur"

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

    The neuron activates on tokens beginning with the substring “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
    琛
    -2.66
     hermanas
    -2.56
    🫃
    -2.53
     pretende
    -2.48
     continuar
    -2.45
     мое
    -2.41
     ก็
    -2.39
    鴬
    -2.38
     manter
    -2.36
    が大
    -2.36
    POSITIVE LOGITS
    0
    3.63
     Because
    3.20
    ’
    2.92
    1
    2.67
    HomeAsUpEnabled
    2.47
    是我的
    2.39
     nadru
    2.38
     meerdere
    2.34
    3
    2.33
    鹄
    2.33
    Activations Density 0.009%

    No Known Activations