© 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. 4522
    Prev
    Next
    INDEX
    Explanations

    system of equations

    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
     بلند
    1.14
    인데요
    1.14
    AppName
    1.10
     GENERAL
    1.08
     प्रयासों
    1.08
     कोहली
    1.06
    ಐ
    1.04
    は約
    1.04
     beträgt
    1.04
     चाहि
    1.03
    POSITIVE LOGITS
     দু
    1.07
    قول
    1.04
    restling
    1.01
     xử
    0.98
    ämä
    0.96
     thấy
    0.96
     poden
    0.96
    雑誌
    0.96
    soap
    0.95
     deixar
    0.95
    Activations Density 0.000%

    No Known Activations