© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    Coefficient tuning, crossed, oxide, powerful, EU

    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
    venu
    1.07
    wast
    1.03
    พันธุ์
    1.03
     која
    1.02
    燊
    1.00
     která
    0.98
    ณ
    0.98
    회
    0.97
     kterou
    0.97
     laquelle
    0.96
    POSITIVE LOGITS
     利用
    1.41
     لا
    1.36
     مفهوم
    1.35
    找到了
    1.35
    യായി
    1.33
    有点
    1.33
     bagus
    1.31
    げて
    1.29
    ებები
    1.28
     Просто
    1.27
    Activations Density 0.000%

    No Known Activations