© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40943
    Prev
    Next
    INDEX
    Explanations

    dehydration and anesthesia

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

    the term "dehydration" and related words about removing water.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is primarily triggered by occurrences of “dehydration” (and its morphological variants).

    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
    o
    -2.94
    y
    -2.77
    al
    -2.77
    我的
    -2.55
    ta
    -2.48
    可以
    -2.45
    \
    -2.42
    翃
    -2.39
    闢
    -2.33
    没有
    -2.31
    POSITIVE LOGITS
    0
    2.61
    酲
    2.52
    戩
    2.36
    ჱ
    2.33
    ญี่ป
    2.33
    淠
    2.25
    阄
    2.25
    当即
    2.23
    崐
    2.23
    だったり
    2.22
    Activations Density 0.007%

    No Known Activations