© 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. 102443
    Prev
    Next
    INDEX
    Explanations

    Bashar al-Assad, Jonathan, Carpe Diem

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

    The neuron strongly activates on pieces of words that form terms expressing fortunate chance—e.g. “serendipitously,” “lucked”/“lucky,” “felicitous”—so it’s picking up words about good luck or serendipity.

    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
    
    -2.38
    Ꭳ
    -2.34
    泐
    -2.17
    ᠊
    -2.16
    ⚋
    -2.13
    蛧
    -2.11
    もしくは
    -2.05
    蹂
    -2.02
    尨
    -1.96
    珝
    -1.95
    POSITIVE LOGITS
    (
    2.20
    .
    2.17
    i
    2.14
    k
    2.09
    b
    2.08
    j
    2.05
    ’
    2.00
    &
    1.99
    ma
    1.98
    w
    1.90
    Activations Density 0.006%

    No Known Activations