© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30197
    Prev
    Next
    INDEX
    Explanations

    HTML tags and links

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

    The main thing this neuron does is identify HTML markup tokens (tags and attribute names).

    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
     Barack
    -0.89
     Wii
    -0.79
    ঙ
    -0.77
    uldron
    -0.77
     ২০১
    -0.77
     favorecer
    -0.76
     odstran
    -0.75
     největ
    -0.75
    打了
    -0.75
    AddWithValue
    -0.75
    POSITIVE LOGITS
     giri
    0.94
    estimable
    0.83
    servlet
    0.80
    ǭ
    0.78
     Rugg
    0.78
     frustra
    0.78
     Malayalam
    0.77
     jugos
    0.77
    JavaScript
    0.77
     kaffe
    0.77
    Activations Density 0.076%

    No Known Activations