© 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. 29784
    Prev
    Next
    INDEX
    Explanations

    veteran or military service

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

    veterans and military

    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
     entrop
    0.52
    🧚
    0.52
    🍌
    0.52
    鼹
    0.47
     corset
    0.47
    🧞
    0.47
    女生
    0.47
    🪐
    0.47
    🧿
    0.46
     Rhiz
    0.46
    POSITIVE LOGITS
     Veterans
    1.51
     veterans
    1.45
     militares
    1.32
     Veteran
    1.30
     Military
    1.28
     military
    1.27
    Military
    1.27
     militaires
    1.27
     militaire
    1.24
    military
    1.23
    Activations Density 0.131%

    No Known Activations