© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23836
    Prev
    Next
    INDEX
    Explanations

    feces, excrement, and poop

    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_40_width_262k_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
    Netflix
    0.41
     Netflix
    0.40
    idental
    0.40
    readValue
    0.39
     Neck
    0.38
    拈
    0.38
     redshift
    0.38
    netflix
    0.37
    Slice
    0.37
    ائرة
    0.36
    POSITIVE LOGITS
     feces
    2.13
     poop
    1.98
     excre
    1.94
    粪
    1.89
     fecal
    1.86
     urine
    1.78
    糞
    1.77
     defec
    1.74
    💩
    1.60
     manure
    1.59
    Activations Density 0.032%

    No Known Activations