© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10288
    Prev
    Next
    INDEX
    Explanations

    my hands or skirt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     أن
    1.63
     بال
    1.63
     в
    1.58
     ومع
    1.57
     ت
    1.54
     وم
    1.52
     وت
    1.51
     ו
    1.51
     По
    1.51
     وأ
    1.50
    POSITIVE LOGITS
    魔法
    1.45
    方法
    1.40
    作品
    1.33
     경우가
    1.30
     법칙
    1.26
    漏
    1.26
    可能性
    1.25
    小的
    1.24
    例子
    1.22
     방법을
    1.22
    Activations Density 0.029%

    No Known Activations