© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118
    Prev
    Next
    INDEX
    Explanations

    urine, piss, and defecation

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

    bodily waste elimination processes and terminology including urination, defecation, and excretion.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.91
    ent
    -1.78
     ….
    -1.65
     THESE
    -1.58
     और
    -1.56
    されて
    -1.55
    ・・・」
    -1.51
     способы
    -1.49
     THIS
    -1.48
    在你
    -1.48
    POSITIVE LOGITS
     ſch
    1.64
     preva
    1.55
     miniaturka
    1.53
     Perubahan
    1.51
     strate
    1.48
     appartamento
    1.48
    铪
    1.48
     básicamente
    1.43
     合集
    1.41
     човек
    1.40
    Activations Density 0.021%

    No Known Activations