© 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. 57267
    Prev
    Next
    INDEX
    Explanations

    fetal heart rate

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

    medical terms related to heart and cardiac function.

    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
     Stell
    -0.73
    ‌ی
    -0.69
    Zu
    -0.69
     Turi
    -0.66
     الش
    -0.66
    atuan
    -0.66
     Mitar
    -0.66
     gauche
    -0.65
    Badge
    -0.65
    ándonos
    -0.64
    POSITIVE LOGITS
     heartbeat
    4.91
    heartbeat
    3.31
     heart
    3.22
    Heartbeat
    3.11
     Heart
    3.06
    心跳
    2.72
     HEART
    2.56
    heart
    2.50
    Heart
    2.48
    HEART
    2.33
    Activations Density 0.041%

    No Known Activations