© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18317
    Prev
    Next
    INDEX
    Explanations

    birth, babies, and family

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

    mentions of reproduction and family formation—pregnancy, giving birth, having children, and related parent/child relationships

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )$
    0.42
     escort
    0.40
    டுப
    0.40
     Interact
    0.40
    Interact
    0.40
    interacting
    0.39
     interacting
    0.38
    ড়
    0.38
     distant
    0.38
     Pence
    0.37
    POSITIVE LOGITS
     births
    0.68
     childbirth
    0.66
    出産
    0.64
     nascita
    0.61
    낳
    0.59
     pregnancies
    0.57
     babies
    0.56
     naissance
    0.55
     nascimento
    0.55
     birth
    0.54
    Activations Density 0.022%

    No Known Activations