© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6046
    Prev
    Next
    INDEX
    Explanations

    pee, urine, and bathrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izados
    0.81
     dacă
    0.79
     daca
    0.77
     पता
    0.76
     đỡ
    0.76
    í
    0.75
    indungan
    0.75
     Arora
    0.75
     vida
    0.74
     I
    0.73
    POSITIVE LOGITS
     incontinence
    1.54
     urination
    1.40
    Toilet
    1.25
     toilet
    1.17
     restroom
    1.17
    尿
    1.16
     feces
    1.15
    toilet
    1.14
     urinal
    1.14
     toilets
    1.11
    Activations Density 0.177%

    No Known Activations