© 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. 4458
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases

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

    рецепт напитка, большой взрыв

    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
    tDBOutput
    0.47
    शंस
    0.46
    <unused59>
    0.46
     প্রতিনিধিত্ব
    0.46
    🏈
    0.46
    ِمض
    0.45
     statunitense
    0.44
     స్థాయిలో
    0.44
    सूचित
    0.44
    अमेरिका
    0.44
    POSITIVE LOGITS
     своими
    0.50
     for
    0.47
     A
    0.47
     homemade
    0.46
     для
    0.46
     in
    0.45
    0.44
    ,
    0.44
    方法
    0.44
     variegated
    0.43
    Activations Density 0.038%

    No Known Activations