© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17061
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thankfulness

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

    gratitude and thankfulness

    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
    ◁
    0.41
    omain
    0.39
    NavItem
    0.39
     inhibitors
    0.38
    ریب
    0.38
    ֻ
    0.38
     inhibiting
    0.36
    olič
    0.36
    诓
    0.36
     আয়
    0.36
    POSITIVE LOGITS
     grateful
    3.36
     gratitude
    3.30
    grateful
    2.97
     thankful
    2.91
     благодар
    2.78
     Grat
    2.55
    感謝
    2.53
     agrade
    2.52
    感恩
    2.52
     কৃতজ্ঞ
    2.50
    Activations Density 0.135%

    No Known Activations