© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159144
    Prev
    Next
    INDEX
    Explanations

    feces, toilets, and plumbing

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

    rectum, anus, feces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     murder
    0.45
     wineries
    0.41
     హత్య
    0.41
     হত্যাকাণ্ড
    0.41
     बेरोजगारी
    0.41
     murders
    0.41
     kredi
    0.40
    ∑
    0.40
     shirts
    0.40
    ドリンク
    0.40
    POSITIVE LOGITS
     feces
    0.95
    肛
    0.90
     fecal
    0.88
    💩
    0.88
     defec
    0.84
     poop
    0.80
     rectum
    0.78
     anus
    0.77
     excre
    0.75
     rectal
    0.75
    Activations Density 0.055%

    No Known Activations