© 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. 47783
    Prev
    Next
    INDEX
    Explanations

    Lei Cham; Lei Ni; thunderstorms

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

    The neuron fires on any token containing the substring “lei,” regardless of its role in the word.

    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
    [
    -3.64
    ly
    -3.47
    .”
    -3.31
    ஂ
    -2.92
    ();
    -2.83
    c
    -2.80
    f
    -2.80
    d
    -2.75
    n
    -2.73
    re
    -2.72
    POSITIVE LOGITS
    珰
    3.36
    鹪
    2.94
    鬭
    2.89
    魆
    2.66
    硨
    2.64
    蹰
    2.63
    湏
    2.61
     kuchen
    2.61
    酲
    2.58
     sinyal
    2.56
    Activations Density 0.003%

    No Known Activations