© 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. 37653
    Prev
    Next
    INDEX
    Explanations

    military weapons and defense contractors

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

    military weapons and modernization programs

    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
    妈妈
    0.57
    诖
    0.56
    哞
    0.55
     Clínica
    0.55
    农
    0.54
    客厅
    0.54
    餐厅
    0.54
    淍
    0.54
    䘚
    0.54
    坫
    0.54
    POSITIVE LOGITS
     military
    1.30
    military
    1.29
    軍
    1.27
     weapons
    1.26
     Military
    1.20
     missile
    1.20
    Military
    1.19
     सैन्य
    1.19
     militaires
    1.17
     militares
    1.16
    Activations Density 0.109%

    No Known Activations