© 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. 10-GEMMASCOPE-RES-131K
    7. 42768
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and greek letters

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

    The neuron activates on Greek-letter angle variables (like “phi” or “theta”) in math 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_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
     to
    -2.33
     or
    -1.35
     in
    -1.35
    section
    -1.29
    那时候
    -1.26
    那时
    -1.24
     ?
    -1.23
     for
    -1.21
     while
    -1.21
      
    -1.20
    POSITIVE LOGITS
    歺
    1.34
    ῞
    1.29
    _
    1.28
    栳
    1.26
    
    1.25
    赑
    1.25
     orilla
    1.20
    ñado
    1.20
    ዑ
    1.20
    莎
    1.18
    Activations Density 0.006%

    No Known Activations