© 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. 10-GEMMASCOPE-RES-131K
    7. 47659
    Prev
    Next
    INDEX
    Explanations

    military forces

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

    The neuron identifies mentions of military forces (e.g. “[Country] forces”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    From
    -2.06
    ↵
    -1.96
    After
    -1.84
     técn
    -1.72
    лость
    -1.63
    because
    -1.61
     every
    -1.57
     sors
    -1.57
    When
    -1.56
     EVERY
    -1.56
    POSITIVE LOGITS
     to
    2.77
     wenigen
    1.75
    
    1.74
     версия
    1.71
     alguns
    1.68
    による
    1.65
    ⸂
    1.65
     possuem
    1.64
    思う
    1.63
    ⾒
    1.63
    Activations Density 0.009%

    No Known Activations