© 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. 5631
    Prev
    Next
    INDEX
    Explanations

    carrying case

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

    examples from multiple languages

    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
    োষণ
    0.29
    NSDictionary
    0.28
    ższ
    0.27
    ริ่ม
    0.27
    ковский
    0.27
    裕
    0.27
    श्य
    0.27
    %%%%%%%%
    0.27
     lysed
    0.27
    得多
    0.27
    POSITIVE LOGITS
     sekal
    0.30
     baloncesto
    0.29
     ٢
    0.28
     lemonade
    0.27
     bothers
    0.27
     (!)
    0.27
     blacksmith
    0.26
     raza
    0.26
     sala
    0.26
     Comenz
    0.26
    Activations Density 0.010%

    No Known Activations