© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10223
    Prev
    Next
    INDEX
    Explanations

    list item separators

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

    dataclasses field

    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_40_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
     mendorong
    0.37
    蔓
    0.36
     کم
    0.35
     arranque
    0.34
    setData
    0.34
    配置文件
    0.34
     करण्यात
    0.33
     Sidebar
    0.33
     swój
    0.33
    setLookAndFeel
    0.33
    POSITIVE LOGITS
     સારી
    0.40
     altijd
    0.40
     महत्
    0.38
    рованное
    0.38
    ALWAYS
    0.37
     …..
    0.37
    ՜
    0.37
     AMAZING
    0.36
    ртуа
    0.36
     ALWAYS
    0.35
    Activations Density 0.001%

    No Known Activations