© 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. 31-GEMMASCOPE-2-RES-262K
    7. 179184
    Prev
    Next
    INDEX
    Explanations

    associated with IDs

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

    SQL table column IDs

    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_31_width_262k_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
     आइटम
    0.38
     les
    0.38
     olan
    0.37
    ණ
    0.37
    实体
    0.37
     فح
    0.37
     الخدمات
    0.37
    奸
    0.37
     règlement
    0.37
     този
    0.36
    POSITIVE LOGITS
     همد
    0.38
     Dip
    0.37
     நூற்றாண்ட
    0.36
     beaded
    0.36
    APPING
    0.36
     инг
    0.36
    Produ
    0.34
     pembang
    0.34
    atural
    0.34
    芏
    0.34
    Activations Density 0.001%

    No Known Activations