© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13709
    Prev
    Next
    INDEX
    Explanations

    could justify

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

    greetings and beginnings

    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_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
     Bạn
    0.61
     ужа
    0.54
     Cela
    0.50
     Restaurants
    0.48
     Tvam
    0.47
     Closeup
    0.46
     你
    0.46
     Yorkshire
    0.46
    妳
    0.46
     Evanston
    0.46
    POSITIVE LOGITS
     complicating
    0.46
     progressively
    0.44
    appliqu
    0.44
    こと
    0.43
    目に
    0.43
    まとめ
    0.43
     radically
    0.43
    認め
    0.43
     &&
    0.42
    arounds
    0.42
    Activations Density 0.001%

    No Known Activations