© 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. 122122
    Prev
    Next
    INDEX
    Explanations

    moderation duties

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

    specific list items or definitions

    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
     شرکت
    0.51
    ட்ரா
    0.51
    ۵
    0.46
    ری
    0.45
     পুনরুদ্ধ
    0.44
    변경된
    0.44
    entities
    0.43
     मोठ
    0.43
     منصوبہ
    0.43
    代わりに
    0.43
    POSITIVE LOGITS
     moder
    0.48
    Moder
    0.48
     trying
    0.45
    ̚
    0.44
     attempting
    0.44
    PNG
    0.44
     moderation
    0.43
     Enlightenment
    0.43
     Moderator
    0.43
    畯
    0.43
    Activations Density 0.001%

    No Known Activations