© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10699
    Prev
    Next
    INDEX
    Explanations

    military conflict and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     воен
    1.32
     squadron
    1.31
    司令
    1.29
    軍
    1.27
    Defence
    1.25
     squadrons
    1.25
    Military
    1.23
     militaire
    1.22
     Defence
    1.22
     Militar
    1.21
    POSITIVE LOGITS
     வாழ்
    0.82
    槃
    0.79
     fixed
    0.78
     Bicycle
    0.78
     bridge
    0.77
     bicycle
    0.77
     ಮೀ
    0.76
     বিশেষজ্ঞ
    0.76
    生态
    0.76
    bicycle
    0.74
    Activations Density 0.117%

    No Known Activations