© 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. 183428
    Prev
    Next
    INDEX
    Explanations

    retro dress, online repair

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

    saltwater intrusion, factions

    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
    ön
    0.55
    สำคัญ
    0.49
     ज्वाइन
    0.48
    อนไลน์
    0.47
    %)$
    0.46
    %/
    0.45
    MISSION
    0.45
    นี้
    0.45
    på
    0.45
    ఈ
    0.45
    POSITIVE LOGITS
     retroactive
    0.56
     retro
    0.47
     swine
    0.47
    纮
    0.44
     generic
    0.44
     continental
    0.44
    犷
    0.42
     Retro
    0.42
    لین
    0.41
     egyptian
    0.41
    Activations Density 0.001%

    No Known Activations