© 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. 12046
    Prev
    Next
    INDEX
    Explanations

    form labels and div elements

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

    The neuron strongly fires on the “<” characters that open HTML (or XML-like) tags.

    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
     forms
    -1.92
     form
    -1.90
    form
    -1.67
     Forms
    -1.67
    Forms
    -1.62
     FORMS
    -1.59
     Form
    -1.56
    forms
    -1.54
     формы
    -1.45
    FORM
    -1.39
    POSITIVE LOGITS
    label
    1.20
     label
    0.99
     labeling
    0.86
     div
    0.84
    labeling
    0.83
    LABEL
    0.78
     LABEL
    0.75
     labels
    0.71
    div
    0.71
    radix
    0.71
    Activations Density 0.009%

    No Known Activations