© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8649
    Prev
    Next
    INDEX
    Explanations

    military readiness and capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    代谢
    0.54
    诊断
    0.53
    坫
    0.51
    遗传
    0.51
     stains
    0.50
    临床
    0.50
    珴
    0.48
    发生的
    0.47
     查询
    0.47
    诊
    0.47
    POSITIVE LOGITS
     troops
    0.93
     armies
    0.92
     militares
    0.88
     tropas
    0.88
    軍
    0.86
     military
    0.86
     army
    0.85
     mobil
    0.81
     infantry
    0.80
     militaires
    0.80
    Activations Density 0.086%

    No Known Activations