© 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. 22-GEMMASCOPE-RES-131K
    7. 13907
    Prev
    Next
    INDEX
    Explanations

    urination and defecation

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

    references to urination, defecation, and bodily waste elimination functions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects words and word parts related to bodily waste elimination (defecation, urination, feces, bladder/bowel movements, incontinence, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    licar
    -1.17
     keinginan
    -1.12
    gin
    -1.10
     where
    -1.09
     already
    -1.05
    随即
    -1.05
    encers
    -1.02
     kebutuhan
    -1.02
    ługa
    -1.02
    junctive
    -1.00
    POSITIVE LOGITS
     bathroom
    1.23
     Bathroom
    1.19
    öten
    1.11
    */
    1.11
     pee
    1.11
    bathroom
    1.11
     conster
    1.09
    onBlur
    1.07
    páns
    1.06
    作曲
    1.05
    Activations Density 0.057%

    No Known Activations