© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78741
    Prev
    Next
    INDEX
    Explanations

    bathroom and toilet facilities

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

    The neuron activates on words and phrases referring to restroom or bathroom facilities and their use.

    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
    SessionManager
    -0.80
    قه
    -0.78
    macro
    -0.76
    zadas
    -0.75
    Filmografie
    -0.74
    daq
    -0.74
    StreetMap
    -0.74
    宫
    -0.73
    VECTOR
    -0.73
    orosi
    -0.72
    POSITIVE LOGITS
     bathroom
    4.06
     bathrooms
    3.70
     toilet
    3.34
     restroom
    3.27
     toilets
    3.22
     restrooms
    3.11
    bathroom
    2.72
     Bathroom
    2.69
     Toilet
    2.48
    Bathroom
    2.39
    Activations Density 0.024%

    No Known Activations