© 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-262K
    7. 4498
    Prev
    Next
    INDEX
    Explanations

    military actions

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

    military, soldiers, infantry

    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_262k_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
     ভোক্তা
    0.39
    波动
    0.39
     بابەت
    0.38
     સમસ્યા
    0.38
     ভোক্ত
    0.37
    睒
    0.36
    诊
    0.35
    诽
    0.35
    房地产
    0.35
     aperiam
    0.35
    POSITIVE LOGITS
     infantry
    1.00
    軍
    0.98
     military
    0.95
     militares
    0.89
     troops
    0.87
     soldiers
    0.86
     militaires
    0.86
     tropas
    0.86
     Infantry
    0.84
    military
    0.83
    Activations Density 0.645%

    No Known Activations