© 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. 111403
    Prev
    Next
    INDEX
    Explanations

    washing

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

    The neuron activates on words referring to washing actions (e.g. wash, washing, washed, rinsing).

    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
    舠
    -1.93
     would
    -1.92
    n
    -1.91
     couldn
    -1.91
    ですので
    -1.88
     could
    -1.86
    苼
    -1.82
     doesn
    -1.82
    v
    -1.77
     seems
    -1.77
    POSITIVE LOGITS
    ↵
    1.87
     treasured
    1.77
    ).”
    1.76
    washing
    1.76
     wash
    1.74
     wykonane
    1.73
    ྂ
    1.71
    蘼
    1.70
     卓
    1.69
     wybór
    1.69
    Activations Density 0.012%

    No Known Activations