© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116384
    Prev
    Next
    INDEX
    Explanations

    tensor symmetry

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

    This neuron detects mentions of a tensor being symmetric—that is, it fires on tokens in statements asserting or defining that a tensor “is symmetric.”

    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
    pherd
    -0.79
    vereignty
    -0.79
    icillin
    -0.73
    toise
    -0.69
    illes
    -0.67
     Sud
    -0.66
    entary
    -0.66
    istema
    -0.66
    Dichloro
    -0.65
    vely
    -0.65
    POSITIVE LOGITS
     symmetric
    1.49
    symmetric
    1.41
    Symmetric
    1.30
     tensor
    1.21
     Symmetric
    1.10
     sym
    1.07
     tensors
    1.03
     asymmetric
    0.99
    tensor
    0.93
    sym
    0.92
    Activations Density 0.016%

    No Known Activations