© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31213
    Prev
    Next
    INDEX
    Explanations

    mathematical constants and integrals

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

    The neuron detects occurrences of the trigonometric variable “θ” (and its domain‐specifying inequalities) in mathematical expressions.

    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
     Lazy
    -0.79
    Lazy
    -0.71
     presunto
    -0.70
     propio
    -0.70
     이야
    -0.69
     malang
    -0.68
    √
    -0.68
     Liszt
    -0.67
     degrees
    -0.66
    pageNumber
    -0.66
    POSITIVE LOGITS
     π
    1.95
    pi
    1.84
     pi
    1.73
    π
    1.69
     PI
    1.21
    
    1.16
    PI
    1.09
     Pi
    1.02
    ipi
    1.00
    Pi
    0.93
    Activations Density 0.020%

    No Known Activations