© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    launching or opening something

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

    new product launches and deployments

    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
     결방
    0.47
    ಕರ
    0.46
    ংখ্যান
    0.45
    风格
    0.44
    扒
    0.44
    삭제
    0.43
     Бога
    0.43
    维生素
    0.42
    ഠ
    0.42
     करूं
    0.42
    POSITIVE LOGITS
     inaugural
    1.20
     Inaug
    1.09
     inaugur
    1.08
     inaug
    1.05
     debut
    1.04
     inaugurated
    0.99
     debuted
    0.98
     debuts
    0.98
     inauguration
    0.96
    デビュー
    0.96
    Activations Density 0.603%

    No Known Activations