© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9921
    Prev
    Next
    INDEX
    Explanations

    operations and assignments

    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_40_width_16k_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
     military
    0.91
     военных
    0.88
    military
    0.88
     воен
    0.87
    Military
    0.83
    軍
    0.82
    军事
    0.81
     militare
    0.80
     軍
    0.80
     Military
    0.79
    POSITIVE LOGITS
     missions
    0.64
     assignments
    0.52
     assegn
    0.52
    operations
    0.50
     Missions
    0.50
     операции
    0.50
    missions
    0.49
     operas
    0.49
     operations
    0.48
     Operations
    0.48
    Activations Density 0.077%

    No Known Activations