© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53903
    Prev
    Next
    INDEX
    Explanations

    bathing and washing

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

    The main thing this neuron does is find references to bathing or washing procedures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    нок
    -0.74
    lico
    -0.74
    textAlignment
    -0.72
     lidar
    -0.71
    ivotopis
    -0.69
    чном
    -0.69
     Evalu
    -0.68
    (",");
    -0.68
    λης
    -0.68
     menswear
    -0.68
    POSITIVE LOGITS
     bath
    4.34
     bathing
    4.25
     bathe
    3.83
     baths
    3.72
     shower
    3.30
     Bathing
    3.19
     wash
    3.11
    bathing
    3.03
     bathed
    2.95
    bath
    2.94
    Activations Density 0.049%

    No Known Activations