© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3409
    Prev
    Next
    INDEX
    Explanations

    index or image IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    サーバ
    1.03
     Hafen
    1.00
    ଣ୍
    0.99
    localize
    0.99
     ジ
    0.97
     biasing
    0.97
     Gleich
    0.96
     Pivot
    0.96
    代謝
    0.96
    大規模
    0.96
    POSITIVE LOGITS
     e
    0.77
     maa
    0.71
     currently
    0.69
     per
    0.68
     well
    0.67
     hình
    0.66
     in
    0.66
    此时
    0.64
     theo
    0.63
     *
    0.63
    Activations Density 0.854%

    No Known Activations