© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99695
    Prev
    Next
    INDEX
    Explanations

    military command and forces

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

    The neuron flags mentions of U.S. military or government entities by picking up uppercase acronyms and organization names (e.g. “U.S.,” “Cyber Command,” “Strategic Air Command”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    factorial
    -0.72
     վ
    -0.70
     ho
    -0.70
    깔
    -0.69
     landscape
    -0.68
     鈴木
    -0.68
    砲
    -0.66
    noindent
    -0.65
     factorial
    -0.65
     Sieg
    -0.65
    POSITIVE LOGITS
     command
    1.68
     Command
    1.67
     commands
    1.48
    Command
    1.38
    command
    1.36
     Commands
    1.35
    commands
    1.29
     commander
    1.23
     коман
    1.23
     COMMAND
    1.20
    Activations Density 0.038%

    No Known Activations