© 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. 81644
    Prev
    Next
    INDEX
    Explanations

    Pauli matrices and quantum mechanics

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

    The neuron fires on numeric tokens and math‐style expressions (digits, parentheses, and formula numbers).

    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
    chave
    -0.83
     грамм
    -0.71
    TextArea
    -0.69
    绒
    -0.67
     Jez
    -0.67
     ам
    -0.65
    plish
    -0.65
    rense
    -0.65
     State
    -0.65
    braz
    -0.65
    POSITIVE LOGITS
     Pauli
    1.33
     matrices
    1.20
    sigma
    1.13
    Pau
    0.95
     sigma
    0.91
     gama
    0.90
    tau
    0.89
     Gell
    0.87
    matrices
    0.87
     generators
    0.85
    Activations Density 0.011%

    No Known Activations