© 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. 80973
    Prev
    Next
    INDEX
    Explanations

    Greek letters and mathematical symbols

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

    The neuron fires on Mathematica‐style escaped symbol tokens (e.g. “\[Pi]”, “\[Tau]”, and their internal numeric codes).

    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
    nbsp
    -0.93
    chtete
    -0.86
    Ւ
    -0.81
    麻辣
    -0.78
    hibi
    -0.76
    货
    -0.75
    を求
    -0.74
    hind
    -0.74
    üy
    -0.74
     обер
    -0.74
    POSITIVE LOGITS
     continúas
    0.77
    Màu
    0.75
    感じが
    0.75
    即便是
    0.75
     meurt
    0.74
    ابة
    0.74
     prevede
    0.74
    trale
    0.71
    arrer
    0.71
     acompañado
    0.71
    Activations Density 0.061%

    No Known Activations