© 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. 90697
    Prev
    Next
    INDEX
    Explanations

    warfare and combat contexts

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

    The neuron responds to words naming military conflict or combat (e.g. “combat,” “battle,” “fighting,” “operations”).

    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
     warfare
    -0.95
     attacks
    -0.94
    赛
    -0.90
     attack
    -0.88
    尝试
    -0.84
     versuchen
    -0.83
     attempted
    -0.82
    ɵ
    -0.81
    ATTACK
    -0.81
    dzić
    -0.81
    POSITIVE LOGITS
     against
    1.18
     prowess
    1.00
     waged
    0.90
     علیه
    0.85
     Preparations
    0.84
     situations
    0.84
     Situations
    0.82
    against
    0.82
    を設置
    0.81
    ίες
    0.81
    Activations Density 0.013%

    No Known Activations