© 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. 10-GEMMASCOPE-RES-131K
    7. 127814
    Prev
    Next
    INDEX
    Explanations

    bathroom facilities

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

    The neuron primarily activates on occurrences of the word “bathroom.”

    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
     was
    -2.95
     где
    -2.58
     —
    -2.55
    他们的
    -2.45
    льным
    -2.36
     について
    -2.33
     Of
    -2.27
     何
    -2.23
    )
    -2.22
    佧
    -2.19
    POSITIVE LOGITS
    姈
    2.94
     vollständ
    2.92
     verkau
    2.75
     sogen
    2.75
     offizi
    2.70
     zusätz
    2.58
    .
    2.56
    别人的
    2.52
    ⽌
    2.48
     anderes
    2.47
    Activations Density 0.002%

    No Known Activations