© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5402
    Prev
    Next
    INDEX
    Explanations

    baby or infant

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

    baby and infants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحصه
    0.47
    塾
    0.43
     учителя
    0.42
    董事
    0.40
     शिक्षक
    0.39
     uczni
    0.39
     председа
    0.39
    གྲ
    0.39
    狡
    0.38
     директора
    0.38
    POSITIVE LOGITS
     baby
    4.38
    baby
    4.09
     Baby
    4.06
    Baby
    3.98
     BABY
    3.89
     babies
    3.83
    婴儿
    3.66
     infant
    3.56
     bebé
    3.52
     Babies
    3.48
    Activations Density 0.381%

    No Known Activations