© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8809
    Prev
    Next
    INDEX
    Explanations

    smart + noun

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

    smart technology and devices

    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
    大战
    0.43
    awr
    0.41
    മ
    0.40
     annih
    0.39
     море
    0.38
     جوا
    0.37
     मक्
    0.37
    ற்று
    0.36
    的世界
    0.36
    砕
    0.35
    POSITIVE LOGITS
     smart
    0.97
     स्मार्ट
    0.90
     Smart
    0.89
    smart
    0.86
     스마트
    0.86
     smarter
    0.83
     スマート
    0.83
     স্মার্ট
    0.77
    Smart
    0.77
     смарт
    0.76
    Activations Density 0.083%

    No Known Activations