© 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. 34-GEMMASCOPE-RES-131K
    7. 57581
    Prev
    Next
    INDEX
    Explanations

    giving birth

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

    text about childbirth, pregnancy, and women giving birth.

    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_34/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
    氡
    -0.74
    ediakan
    -0.71
    łości
    -0.71
    noc
    -0.70
     difp
    -0.69
    ุ่ง
    -0.68
     Rhin
    -0.67
    ículas
    -0.67
    boli
    -0.66
    幸いです
    -0.65
    POSITIVE LOGITS
     giving
    3.08
    Giving
    2.84
     gave
    2.78
     give
    2.73
    giving
    2.67
     Giving
    2.56
     melahirkan
    2.53
     birth
    2.47
    Give
    2.41
     childbirth
    2.33
    Activations Density 0.061%

    No Known Activations