© 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. 34-GEMMASCOPE-RES-131K
    4. 602
    Prev
    Next
    INDEX
    Explanations

    spring bean creation

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

    The neuron fires on XML namespace‐declaration tokens (e.g. the “xmlns” attributes and related schema URLs in Spring bean XML).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     impati
    -0.86
     심
    -0.85
    patra
    -0.82
     saffron
    -0.79
     prac
    -0.78
     keg
    -0.77
     reconstructions
    -0.76
    ætte
    -0.75
     Speer
    -0.75
    JST
    -0.75
    POSITIVE LOGITS
     év
    0.77
    醤
    0.76
    Bean
    0.73
     Bean
    0.72
     harassed
    0.70
    𝑜
    0.70
     nieruch
    0.70
     Интернет
    0.69
    Muon
    0.69
     роли
    0.68
    Activations Density 0.011%

    No Known Activations