© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    clothing styles and attire

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

    apparel and clothing

    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
    䧉
    0.44
     stoichi
    0.43
     sureties
    0.42
    𒀀
    0.42
     triphosphate
    0.41
     bittern
    0.41
     प्रक्रियाओं
    0.41
    맺
    0.40
     denitr
    0.40
    𒂍
    0.40
    POSITIVE LOGITS
     dresses
    2.67
     dress
    2.64
     পোশাক
    2.56
     clothing
    2.48
     attire
    2.47
     clothes
    2.44
     vêtements
    2.42
     옷
    2.42
     لباس
    2.34
     roupas
    2.34
    Activations Density 0.897%

    No Known Activations