© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14529
    Prev
    Next
    INDEX
    Explanations

    bodily waste and genitalia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    谋
    0.49
    Murder
    0.46
    🔪
    0.46
     LinkedIn
    0.45
     SLA
    0.44
     murder
    0.44
     убий
    0.43
     Murder
    0.41
     murderous
    0.41
     Violence
    0.41
    POSITIVE LOGITS
    🚽
    1.15
     toilet
    1.12
     fecal
    1.10
     urine
    1.09
     feces
    1.08
     urinary
    1.06
     potty
    1.06
     मूत्र
    1.05
     excre
    1.03
     Urine
    0.98
    Activations Density 0.237%

    No Known Activations