© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39027
    Prev
    Next
    INDEX
    Explanations

    XML namespaces

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

    The neuron detects XML namespace declarations (the “xmlns” attributes and their URI assignments).

    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
    }
    -2.16
     if
    -1.80
     how
    -1.66
     $
    -1.55
    indahan
    -1.55
     работают
    -1.52
    );
    -1.51
    一个
    -1.48
     out
    -1.45
     
    -1.42
    POSITIVE LOGITS
     али
    1.68
    ⦊
    1.64
    ógica
    1.53
    昞
    1.49
    郇
    1.49
     incrí
    1.49
    demás
    1.47
    Itoa
    1.45
     Поэтому
    1.44
    鲮
    1.44
    Activations Density 0.028%

    No Known Activations