© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60036
    Prev
    Next
    INDEX
    Explanations

    equation alignment environments

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

    The neuron fires on LaTeX environment openings—that is, the “{” tokens immediately following \begin (e.g. in begin{align}, begin{array}, begin{matrix}, begin{cases}, etc.).

    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
    cree
    -0.94
    Polic
    -0.87
     ذه
    -0.86
    meine
    -0.83
     PLAYING
    -0.82
     Camry
    -0.79
    (/[
    -0.78
     MOND
    -0.78
     yeti
    -0.77
     randon
    -0.77
    POSITIVE LOGITS
    aligned
    0.96
     aligns
    0.81
     aligned
    0.80
     hôm
    0.79
     evaluate
    0.77
     gustaría
    0.77
     align
    0.76
     シャンプー
    0.76
    <blockquote>
    0.75
     his
    0.75
    Activations Density 0.001%

    No Known Activations