© 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. 116954
    Prev
    Next
    INDEX
    Explanations

    android namespaces in XML

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

    This neuron detects code‐style tokens—identifiers, constants, and keywords you’d find in programming or markup (e.g. filenames, macros, XML attributes, namespaces).

    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
    several
    -0.77
    phrase
    -0.75
     manifold
    -0.74
     SYSTEM
    -0.74
    ctives
    -0.70
    Handle
    -0.70
     hart
    -0.69
     strepto
    -0.69
     Handle
    -0.69
     attendant
    -0.68
    POSITIVE LOGITS
    čená
    0.67
    んご
    0.66
    assic
    0.64
     utrzy
    0.64
    llc
    0.63
    שׁ
    0.62
     FDR
    0.62
     Elek
    0.62
    ście
    0.62
     Posi
    0.61
    Activations Density 0.047%

    No Known Activations