© 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
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11649
    Prev
    Next
    INDEX
    Explanations

    bodily waste and toilet

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

    diarrhea and related excretions

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

    bathroom/bodily waste

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Netflix
    0.45
    噬
    0.39
    ghost
    0.38
    bhl
    0.38
    Dust
    0.37
    netflix
    0.37
    Sony
    0.37
     रमेश
    0.36
     জুল
    0.36
    肩
    0.36
    POSITIVE LOGITS
     feces
    2.03
     toilet
    1.99
     defec
    1.89
     fecal
    1.88
     poop
    1.88
     Toilet
    1.88
    🚽
    1.87
     excre
    1.81
     toilets
    1.80
    toilet
    1.77
    Activations Density 0.308%

    No Known Activations