© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 344
    Prev
    Next
    INDEX
    Explanations

    Multilingual prompts and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    之
    0.50
     ιστο
    0.50
    الم
    0.49
    式
    0.48
    文本
    0.46
    单元
    0.46
    色の
    0.46
     المح
    0.44
    视图
    0.44
     مجموعة
    0.43
    POSITIVE LOGITS
    把自己
    0.68
    拿出
    0.65
     đem
    0.64
    把它
    0.62
    把
    0.61
    拿着
    0.60
    抱着
    0.60
    拿到
    0.60
    拿
    0.58
    把他
    0.56
    Activations Density 0.018%

    No Known Activations