© 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. 65290
    Prev
    Next
    INDEX
    Explanations

    epsilon

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

    The neuron strongly activates on occurrences of the Greek letter “epsilon” used as a mathematical or scientific variable.

    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
     ‘
    -2.64
    ,”
    -2.36
     sooo
    -2.34
    ：“
    -2.28
    ωση
    -2.27
    y
    -2.27
    奩
    -2.27
     pomo
    -2.23
     millioner
    -2.23
    НЫХ
    -2.16
    POSITIVE LOGITS
     When
    2.44
    籐
    2.39
     After
    2.39
    EDEFAULT
    2.36
     przygoto
    2.22
     Following
    2.22
     französische
    2.22
    n
    2.20
     После
    2.17
     ਅਤੇ
    2.16
    Activations Density 0.001%

    No Known Activations