© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63153
    Prev
    Next
    INDEX
    Explanations

    WeChat and QQ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tigem
    -0.77
     pungent
    -0.75
    Condu
    -0.74
    каль
    -0.72
    ул
    -0.68
    川崎
    -0.68
     unchanging
    -0.68
    washington
    -0.68
    poel
    -0.67
    Washington
    -0.66
    POSITIVE LOGITS
     WeChat
    2.72
    微信
    1.91
     QQ
    1.81
    WeChat
    1.75
    qq
    1.75
     wx
    1.69
    wx
    1.68
    QQ
    1.66
    weixin
    1.66
     qq
    1.61
    Activations Density 0.033%

    No Known Activations