© 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. 16780
    Prev
    Next
    INDEX
    Explanations

    pregnancy and birth

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

    pregnancy and maternity

    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
     پیر
    0.48
     ചൂ
    0.46
    弑
    0.43
    勉
    0.43
     अहि
    0.42
     ছাত্রদের
    0.42
     мел
    0.41
    吃飯
    0.41
    ጠቀም
    0.41
    冪
    0.40
    POSITIVE LOGITS
    🤰
    1.63
    妊娠
    1.56
     maternity
    1.55
     pregnancy
    1.55
     pregnant
    1.47
     Pregnancy
    1.47
     беремен
    1.47
     pregnancies
    1.41
     Maternity
    1.41
     embarazo
    1.41
    Activations Density 0.172%

    No Known Activations