© 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. 102712
    Prev
    Next
    INDEX
    Explanations

    metric indexes like mu

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

    The neuron is triggered by LaTeX-style metric tensor notation (e.g. g_{μν}) and related mathematical symbols in physics equations.

    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
     Liverpool
    -0.97
    neden
    -0.89
     Saudi
    -0.82
    intios
    -0.81
     investment
    -0.79
    SuspendLayout
    -0.79
     Environmental
    -0.78
    alaman
    -0.77
    ijnen
    -0.76
    velocityY
    -0.76
    POSITIVE LOGITS
    μ
    1.09
    mu
    0.90
    𝜇
    0.86
     µ
    0.85
     μ
    0.83
    omu
    0.78
    µ
    0.77
    ^{\
    0.74
     mu
    0.74
     누
    0.73
    Activations Density 0.011%

    No Known Activations