© 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. 127451
    Prev
    Next
    INDEX
    Explanations

    wetting and wetness

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

    The neuron strongly activates on any form of the word “wet” (e.g. “wet,” “wetting,” “wettable,” etc.).

    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
    er
    -2.25
    コスト
    -1.93
    In
    -1.86
    le
    -1.80
    u
    -1.73
     provide
    -1.67
     reap
    -1.66
    {
    -1.62
    .”
    -1.59
    Y
    -1.59
    POSITIVE LOGITS
    縢
    2.02
    很赞
    2.02
    ₶
    1.97
    沨
    1.91
    宬
    1.89
    夘
    1.84
    wet
    1.83
     рамках
    1.82
    
    1.77
     unſ
    1.74
    Activations Density 0.011%

    No Known Activations