© 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. 117982
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and licensing

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

    The neuron fires on LaTeX mathematical formatting commands (e.g. begin‐array, pmatrix, binom).

    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
     アウト
    -0.73
     oppure
    -0.71
    бую
    -0.71
    묶
    -0.71
    рисов
    -0.69
    plen
    -0.68
    čin
    -0.68
     選手
    -0.68
    cios
    -0.67
     Euros
    -0.67
    POSITIVE LOGITS
    ֽ
    0.90
    Shortest
    0.81
     []).
    0.78
    atch
    0.75
     тр
    0.74
    icha
    0.73
    ACK
    0.73
    водит
    0.73
    mee
    0.72
    ctivas
    0.71
    Activations Density 0.002%

    No Known Activations