© 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. 108885
    Prev
    Next
    INDEX
    Explanations

    military operations and entities

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of military-related terms, especially the word “military.”

    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
    WAR
    -0.88
     войска
    -0.80
     produisent
    -0.79
    修炼
    -0.76
     demandent
    -0.75
     hätte
    -0.75
    tranh
    -0.74
    PAR
    -0.74
    čilo
    -0.74
     蜜
    -0.73
    POSITIVE LOGITS
     actions
    1.00
     hardware
    0.91
     collaboration
    0.91
     action
    0.90
     atta
    0.88
     solution
    0.88
     establishment
    0.88
     necessity
    0.88
     operations
    0.87
     success
    0.86
    Activations Density 0.014%

    No Known Activations