© 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. 4399
    Prev
    Next
    INDEX
    Explanations

    handmade items and Etsy

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

    read the disclaimer

    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
     promulgating
    0.54
     ostensibly
    0.48
     值
    0.47
     ましょう
    0.46
     efficacious
    0.46
     citizenry
    0.45
     promulgate
    0.45
    記者
    0.45
    relatively
    0.44
     paucity
    0.44
    POSITIVE LOGITS
     Etsy
    1.23
     Handmade
    1.16
     handmade
    1.13
     etsy
    1.11
     ♡
    1.01
    handmade
    0.96
     handcrafted
    0.94
     ❤️
    0.90
    ❤️
    0.90
    ♡
    0.89
    Activations Density 0.434%

    No Known Activations