© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8766
    Prev
    Next
    INDEX
    Explanations

    said.added

    np_acts-logits-general · gemini-2.5-flash-lite

    latest news updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     Вот
    0.31
    㳡
    0.30
     বাঙ্গালী
    0.30
     Southerners
    0.30
    Whoever
    0.29
     Whoever
    0.29
    শাল
    0.28
    是怎么
    0.28
    了这个
    0.28
     BOTH
    0.28
    POSITIVE LOGITS
    kli
    0.32
    にて
    0.30
    dyna
    0.29
    design
    0.29
    klu
    0.29
    ک
    0.29
    eval
    0.28
     নিরাপদ
    0.28
     ஏற்பட்ட
    0.28
     whereby
    0.28
    Activations Density 0.040%

    No Known Activations