© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    note many accepted

    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
    Kui
    1.35
    ặ
    1.27
     مللي
    1.24
    ầ
    1.23
    Baca
    1.22
    ￱
    1.22
     zariaden
    1.20
    اسية
    1.18
    Hozzáférés
    1.17
    ExposureTime
    1.15
    POSITIVE LOGITS
     不
    1.50
     在
    1.47
     你
    1.40
     如果
    1.37
     我
    1.37
     小
    1.36
     或
    1.34
     不是
    1.34
     从
    1.32
     若
    1.31
    Activations Density 0.009%

    No Known Activations