© 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. 50355
    Prev
    Next
    INDEX
    Explanations

    linear differential equations

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

    The neuron activates on technical mathematical terminology, especially words around linear (and linearly independent) systems, homogeneous solutions, and differential 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
    Customs
    -0.90
    čené
    -0.76
     уг
    -0.75
    then
    -0.75
    věr
    -0.73
     andes
    -0.73
    warp
    -0.73
     propagated
    -0.72
     Nieto
    -0.70
    decoded
    -0.70
    POSITIVE LOGITS
     coefficients
    0.98
     coefficient
    0.86
    coefficient
    0.83
     differential
    0.79
    Linear
    0.79
     Linear
    0.79
    coef
    0.77
     linear
    0.75
    OuterClass
    0.74
    干嘛
    0.73
    Activations Density 0.042%

    No Known Activations