© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    DoD instructions and commanders

    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_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
     ব্যবসার
    0.49
     पेमेंट
    0.49
     ఉద్య
    0.49
     금융
    0.48
    isVideoRecording
    0.48
    赠
    0.48
     联系
    0.47
    ní
    0.47
    ریٹر
    0.47
    Tính
    0.47
    POSITIVE LOGITS
     DoD
    1.11
     commanders
    1.05
     civilian
    1.04
     Army
    0.99
     USAF
    0.96
    Army
    0.94
    Military
    0.91
     doctrinal
    0.89
     commander
    0.88
     военно
    0.87
    Activations Density 0.173%

    No Known Activations