© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 583
    Prev
    Next
    INDEX
    Explanations

    military conflict/warfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    🎢
    0.77
    Phenyl
    0.76
     зарегистри
    0.76
     निवेशकों
    0.73
     ünivers
    0.73
    ifestyle
    0.72
     Público
    0.70
    🤸
    0.68
    🔮
    0.68
     ассоциа
    0.68
    POSITIVE LOGITS
     infantry
    2.57
     Infantry
    2.25
     artillery
    2.22
     troops
    2.15
     battlefield
    2.14
     commanders
    2.05
     soldiers
    2.02
     battalion
    1.98
     전투
    1.97
     combat
    1.90
    Activations Density 0.969%

    No Known Activations