© 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. 164646
    Prev
    Next
    INDEX
    Explanations

    halftime show

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

    singing karaoke

    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
    鄉
    0.51
    знав
    0.50
    രുവ
    0.46
     pic
    0.45
     conoce
    0.44
     caravans
    0.44
     generasi
    0.43
     conhe
    0.43
    公子
    0.42
    عهد
    0.42
    POSITIVE LOGITS
     ट्रॉ
    0.48
    orrhea
    0.47
    აზე
    0.45
    🔔
    0.44
    多个
    0.44
    astom
    0.44
     آن‌ها
    0.44
    一般来说
    0.44
    ().
    0.44
     قاسمی
    0.43
    Activations Density 0.000%

    No Known Activations