Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12330
    Prev
    Next
    INDEX
    Explanations

    childbirth and delivery management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     Patreon
    0.41
     miesięcy
    0.40
     নিত্য
    0.40
     jīn
    0.39
     potted
    0.39
    🐜
    0.39
     grew
    0.38
     месе
    0.38
     tumeur
    0.38
     Merchandise
    0.38
    POSITIVE LOGITS
     obstetric
    1.13
     childbirth
    1.11
     postpartum
    1.07
     vaginal
    1.05
    accouchement
    1.04
     forceps
    1.02
     births
    0.96
    娩
    0.95
     midwives
    0.94
     midwife
    0.93
    Activations Density 0.010%

    No Known Activations