© 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. 22-GEMMASCOPE-RES-131K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    html tag closing or code syntax

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

    This neuron detects code-like syntax snippets (e.g. HTML/XML tags and attribute tokens, code keywords, indent markers) in technical posts.

    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
     only
    -1.36
     during
    -1.24
     when
    -1.10
     in
    -1.10
     this
    -1.08
     who
    -1.05
     before
    -1.05
     ONLY
    -1.05
     from
    -1.05
     componentes
    -0.96
    POSITIVE LOGITS
     deliciously
    0.94
     prachtige
    0.94
     unn
    0.92
     severa
    0.90
     Однако
    0.90
     Hertfordshire
    0.87
    Deel
    0.87
     revamped
    0.87
    ねー
    0.87
     NOP
    0.87
    Activations Density 0.033%

    No Known Activations