© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13538
    Prev
    Next
    INDEX
    Explanations

    bodily waste and excretion

    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_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
    谋
    0.47
     Lieb
    0.45
    電機
    0.45
    Murder
    0.44
     ప్రేమ
    0.42
    🔪
    0.41
     Loren
    0.40
    violence
    0.40
    規模
    0.39
     murder
    0.39
    POSITIVE LOGITS
     fecal
    1.16
    🚽
    1.16
     toilet
    1.13
     feces
    1.13
     potty
    1.10
     excre
    1.05
    💩
    1.02
     urine
    0.99
     excreted
    0.94
    Toilet
    0.93
    Activations Density 0.335%

    No Known Activations