© 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-262K
    7. 10392
    Prev
    Next
    INDEX
    Explanations

    military generals

    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_262k_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
     monetize
    0.58
     fintech
    0.57
     Fintech
    0.55
     ভোক্তা
    0.53
     monetization
    0.53
     sweeteners
    0.52
    🛋
    0.52
     মার্কে
    0.52
     sweetener
    0.52
     ভোক্ত
    0.51
    POSITIVE LOGITS
     military
    2.50
    Military
    2.34
     Military
    2.30
    military
    2.25
     militares
    2.22
    軍
    2.20
     militari
    2.11
     militaire
    2.09
     militaires
    2.08
     militare
    2.03
    Activations Density 0.029%

    No Known Activations