© 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. 34-GEMMASCOPE-RES-131K
    7. 59532
    Prev
    Next
    INDEX
    Explanations

    open defecation and toilets

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

    words and phrases related to human waste, toilets, and sewage.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Firewall
    -0.88
     spurious
    -0.80
     firewall
    -0.79
    marginVertical
    -0.78
    xdf
    -0.76
    alai
    -0.75
     governor
    -0.75
     proton
    -0.75
     Collision
    -0.74
     הארץ
    -0.74
    POSITIVE LOGITS
     toilet
    2.08
     toilets
    2.02
     sewage
    2.02
     fecal
    1.83
     Toilet
    1.65
     excre
    1.63
     feces
    1.59
     poop
    1.58
     sewer
    1.57
     wastewater
    1.57
    Activations Density 0.026%

    No Known Activations