© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11550
    Prev
    Next
    INDEX
    Explanations

    Baby followed by words

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

    baby, babe, or baby-related phrases

    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_40_width_16k_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
    ensively
    0.45
    മിതി
    0.43
    étr
    0.43
     میزان
    0.39
    வாள
    0.39
     {
    0.38
    педи
    0.38
     שני
    0.38
    SIBLE
    0.38
     ん
    0.38
    POSITIVE LOGITS
     boomers
    0.50
    休憩
    0.46
     bab
    0.45
     Carriage
    0.44
     elef
    0.43
     الشعر
    0.42
    摫
    0.42
     Bab
    0.42
     carriage
    0.41
    carriage
    0.41
    Activations Density 0.048%

    No Known Activations