© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81364
    Prev
    Next
    INDEX
    Explanations

    arms, weapons, gun violence

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

    The neuron strongly activates on words and phrases related to arms, weapons, and defense equipment (e.g. defense exports, dual‐use goods, weapons proliferation).

    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
     häls
    -0.84
    褴
    -0.80
     protocole
    -0.79
    setAdapter
    -0.78
    adapter
    -0.78
    ማ
    -0.75
    vien
    -0.75
     UFC
    -0.74
    ắ
    -0.74
    暉
    -0.74
    POSITIVE LOGITS
     arms
    1.87
     Arms
    1.55
    Arms
    1.50
    arms
    1.43
     weapons
    1.29
     ARMS
    1.13
     broker
    1.08
     caches
    1.07
     arsen
    1.07
     cache
    1.03
    Activations Density 0.011%

    No Known Activations