© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4245
    Prev
    Next
    INDEX
    Explanations

    pregnancy and fetal development

    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_31_width_16k_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
     問
    0.45
    brought
    0.44
     brought
    0.41
    弃
    0.41
     Franchise
    0.40
    Chuck
    0.39
    authored
    0.39
     récupérer
    0.39
     യുവാ
    0.39
     ে
    0.39
    POSITIVE LOGITS
     fetal
    0.61
     ultrasound
    0.57
     weekly
    0.55
     embryo
    0.55
     detectable
    0.54
     ultrasonic
    0.54
     weeks
    0.54
     early
    0.52
    胎
    0.52
    weekly
    0.52
    Activations Density 0.119%

    No Known Activations