© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30620
    Prev
    Next
    INDEX
    Explanations

    TikTok, Douyin, live, shop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HRIM
    0.43
    Fach
    0.43
    ӹ
    0.42
    Angular
    0.41
    Pixel
    0.41
    VIDIA
    0.41
    arctica
    0.41
     episcop
    0.40
    槙
    0.40
    Visual
    0.40
    POSITIVE LOGITS
     TikTok
    0.78
     tiktok
    0.69
    TikTok
    0.68
     Tiktok
    0.68
    tiktok
    0.56
    抖音
    0.53
    iktok
    0.52
     Creole
    0.44
     Tik
    0.43
     troupes
    0.41
    Activations Density 0.252%

    No Known Activations