© 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. 34-GEMMASCOPE-RES-131K
    7. 84686
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations

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

    The neuron activates on pieces of web or XML namespace URIs (e.g. “http://www.…”)—in other words, it’s looking for URL/namespace strings.

    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
    www
    -1.23
     gesetzt
    -0.98
    还在
    -0.93
    都會
    -0.93
    を
    -0.91
     ¹
    -0.91
    adresse
    -0.90
    ariana
    -0.90
    といいます
    -0.85
    ANTO
    -0.84
    POSITIVE LOGITS
     måske
    1.13
     tieto
    0.94
     JUST
    0.93
     exemplos
    0.91
    Maybe
    0.89
    example
    0.89
    èmes
    0.89
    一定的
    0.88
        
    0.88
     ejemplos
    0.88
    Activations Density 0.043%

    No Known Activations