© 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. 17733
    Prev
    Next
    INDEX
    Explanations

    clothing colors and items

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

    clothing items and styles

    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
     black
    0.63
     블랙
    0.57
    黑色
    0.54
     কালো
    0.53
     blackened
    0.53
     чор
    0.52
    ブラック
    0.51
    黑
    0.49
    black
    0.48
     чёр
    0.48
    POSITIVE LOGITS
    IDField
    0.42
    ुरे
    0.42
    ("@
    0.37
    வ்வேறு
    0.37
    䒨
    0.37
     hen
    0.37
    herald
    0.36
     Hen
    0.36
    barn
    0.35
    ူး
    0.35
    Activations Density 0.004%

    No Known Activations