© 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. 138427
    Prev
    Next
    INDEX
    Explanations

    in for particular

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

    dates and effective times

    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
     הראשון
    0.43
     Лондон
    0.43
     Londres
    0.43
     লন্ডন
    0.43
    Ꮼ
    0.43
     Nisan
    0.42
     Xiaomi
    0.42
     Armour
    0.42
     Grundlagen
    0.41
     TComponent
    0.41
    POSITIVE LOGITS
    時候
    0.54
    的時候
    0.52
    OR
    0.48
    ότερα
    0.43
    determination
    0.43
    IV
    0.43
    poon
    0.43
    歎
    0.43
     splashes
    0.42
    之間
    0.41
    Activations Density 0.001%

    No Known Activations