© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2470
    Prev
    Next
    INDEX
    Explanations

    Chinese tech and social media

    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_16k_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
    暠
    0.54
    朊
    0.53
    ysteine
    0.52
    輥
    0.51
    劒
    0.50
    Critical
    0.49
    禳
    0.48
    Kö
    0.48
     семина
    0.48
    闡
    0.48
    POSITIVE LOGITS
     WeChat
    0.85
    微信
    0.84
    小程序
    0.76
    wx
    0.73
     Tencent
    0.65
     wx
    0.61
    weixin
    0.59
    手机
    0.57
    openid
    0.56
    抖音
    0.55
    Activations Density 0.060%

    No Known Activations