© 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-16K
    7. 12904
    Prev
    Next
    INDEX
    Explanations

    programming functions and delegates

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

    code blocks ending

    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_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
    respect
    0.45
    िलों
    0.42
    還可以
    0.42
    穢
    0.40
    ローブ
    0.39
    inform
    0.39
    鳴
    0.39
    の場合
    0.38
    嘔
    0.38
     サイド
    0.38
    POSITIVE LOGITS
     تعین
    0.43
     drilled
    0.41
     Satt
    0.41
     errorHandler
    0.41
    ",[(
    0.40
     Initially
    0.40
     propagated
    0.40
     anaerobic
    0.39
     contractName
    0.39
    ərə
    0.39
    Activations Density 0.015%

    No Known Activations