© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72544
    Prev
    Next
    INDEX
    Explanations

    genitals and related anatomy

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

    anatomical terminology related to genitalia and reproductive organs.

    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
    蔸
    -1.50
    ).}
    -1.16
     least
    -1.14
    ducati
    -1.13
     entire
    -1.13
    enerated
    -1.11
    trang
    -1.10
     actual
    -1.09
    気付
    -1.09
    estament
    -1.07
    POSITIVE LOGITS
     Whenever
    1.27
    Ϻ
    1.24
    ají
    1.20
    
    1.17
     cerevisiae
    1.16
    yscy
    1.16
    Проце
    1.15
    illado
    1.14
    quíni
    1.14
    jeuner
    1.13
    Activations Density 0.048%

    No Known Activations