© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    words starting with mys

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

    The neuron strongly responds to the substring “Mys” (as a token or prefix) in words like “Mystics,” “Mystikal,” or “Mystique.”

    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
     It
    -3.36
    )-
    -3.05
    </sup>
    -2.94
    -2.92
    ){
    -2.86
     is
    -2.67
     you
    -2.52
    "
    -2.45
     ,
    -2.39
    賂
    -2.39
    POSITIVE LOGITS
     habile
    2.94
     “(
    2.67
     炖
    2.67
     “[
    2.63
     撮っ
    2.63
     humeur
    2.52
    Ирина
    2.52
    鮃
    2.44
    艫
    2.42
    
    2.36
    Activations Density 0.005%

    No Known Activations