© 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. 57499
    Prev
    Next
    INDEX
    Explanations

    washing

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

    The neuron specifically fires on occurrences of “washing” (and closely related wash‐water contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    terms related to washing/cleaning processes and contexts, including laundering actions, wash cycles, and appliances or water used for washing.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "washing" or its variations (like "washed").

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    .”
    -3.11
    鄚
    -2.89
     其他
    -2.88
    睃
    -2.78
    樒
    -2.69
    儅
    -2.66
    ですので
    -2.59
    泂
    -2.55
    茑
    -2.52
    鲧
    -2.52
    POSITIVE LOGITS
    別人
    2.69
    -
    2.63
    ).”
    2.61
     variety
    2.52
     multitude
    2.48
     знали
    2.31
    觊
    2.31
     ситуации
    2.31
     dasarnya
    2.30
     mezcla
    2.28
    Activations Density 0.005%

    No Known Activations