© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109103
    Prev
    Next
    INDEX
    Explanations

    fetal distress and complications

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

    medical terminology related to pregnancy, childbirth, and fetal monitoring.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on long, specialized medical terminology—especially multi-syllable words related to perinatal and fetal health and monitoring.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     actively
    -0.75
    ━━━━━━━━
    -0.69
     if
    -0.68
     смотря
    -0.68
     Procedure
    -0.68
     verify
    -0.66
     first
    -0.66
     XXX
    -0.66
    faa
    -0.66
     amargo
    -0.65
    POSITIVE LOGITS
    kick
    0.93
     Fetal
    0.90
    strip
    0.87
    baby
    0.87
    CTG
    0.86
     Wellbeing
    0.85
     filós
    0.84
    Bernie
    0.83
     strip
    0.81
    Baby
    0.81
    Activations Density 0.043%

    No Known Activations