© 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. 34910
    Prev
    Next
    INDEX
    Explanations

    military service and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    fiez
    -0.79
    женская
    -0.76
    ägen
    -0.75
     Meksiko
    -0.75
    緊急
    -0.74
    lecht
    -0.73
    aterna
    -0.72
    刺客
    -0.72
    SETUP
    -0.71
    iesc
    -0.71
    POSITIVE LOGITS
     military
    4.06
    military
    3.42
     Military
    3.20
     Army
    3.16
    Military
    3.14
     army
    2.77
     soldiers
    2.64
    Army
    2.61
     soldier
    2.50
     militaire
    2.50
    Activations Density 0.298%

    No Known Activations