© 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. 10-GEMMASCOPE-RES-131K
    7. 73120
    Prev
    Next
    INDEX
    Explanations

    greek letter phi and mathematical notation

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

    This neuron detects occurrences of the Greek letter “phi” (φ) used as a mathematical symbol.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ch
    -2.63
    t
    -2.59
    of
    -2.42
     примерно
    -2.36
     een
    -2.27
     are
    -2.25
    or
    -2.22
    per
    -2.20
    賒
    -2.19
    鷓
    -2.17
    POSITIVE LOGITS
    ୬
    2.59
    驺
    2.55
    ühnen
    2.50
    และ
    2.50
    л
    2.42
    ⢊
    2.30
    맑
    2.23
    \
    2.22
    ᆞ
    2.20
     técnico
    2.19
    Activations Density 0.002%

    No Known Activations