© 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. 17077
    Prev
    Next
    INDEX
    Explanations

    TikTok fashion and products

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

    aesthetic and niche interests

    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
     superbly
    0.55
    绍
    0.52
    滗
    0.48
     Incidentally
    0.45
    Incidentally
    0.45
     appropriately
    0.43
    呵呵
    0.43
    DVD
    0.43
     terrific
    0.42
     करीत
    0.42
    POSITIVE LOGITS
     TikTok
    1.32
     tiktok
    1.30
    🫶
    1.26
     Tiktok
    1.24
    🥹
    1.16
    TikTok
    1.14
    tiktok
    1.13
    🥺
    1.12
    🤍
    1.04
    🥲
    1.01
    Activations Density 0.099%

    No Known Activations