© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34861
    Prev
    Next
    INDEX
    Explanations

    xml meta tags

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

    This neuron detects the opening angle bracket “<” of XML/HTML tags, with stronger activations for more deeply nested tag openings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Bretaña
    -1.60
     hunde
    -1.53
    haviours
    -1.41
     türkiye
    -1.39
     plafon
    -1.39
    LEBR
    -1.38
     metais
    -1.33
     to
    -1.32
     endforeach
    -1.30
     berken
    -1.30
    POSITIVE LOGITS
     These
    1.41
    L
    1.32
     Эти
    1.30
    N
    1.25
     essas
    1.25
     öst
    1.23
    I
    1.22
    These
    1.21
     dessas
    1.21
    C
    1.20
    Activations Density 0.015%

    No Known Activations