© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44236
    Prev
    Next
    INDEX
    Explanations

    the word weird

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

    The neuron is specifically detecting the word “Weird.”

    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
    訁
    -2.59
    ݯ
    -2.59
    ⤥
    -2.53
     Besonder
    -2.52
    
    -2.47
    怎么回事
    -2.45
    剮
    -2.39
    dott
    -2.33
    м
    -2.20
    (
    -2.16
    POSITIVE LOGITS
    鹛
    2.66
    .
    2.36
    寕
    2.34
    ！”
    2.25
    鬭
    2.22
     With
    2.20
    硨
    2.16
    '
    2.06
    ताओं
    2.03
    y
    2.03
    Activations Density 0.004%

    No Known Activations