© 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. 98111
    Prev
    Next
    INDEX
    Explanations

    chiefs of staff and commanders

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

    The neuron fires on formal mentions of military ranks, titles, and high-level defense positions.

    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
    ambo
    -0.80
    elson
    -0.79
     gründ
    -0.74
     patter
    -0.73
    lė
    -0.71
     Silly
    -0.71
     カジュアル
    -0.69
     lauter
    -0.69
    信用
    -0.67
    कृत
    -0.67
    POSITIVE LOGITS
     Chief
    1.77
    Chief
    1.73
     Chiefs
    1.60
     chiefs
    1.48
     chief
    1.41
    chief
    1.17
     CHIEF
    1.06
    chiefs
    1.04
     Army
    0.94
     army
    0.91
    Activations Density 0.029%

    No Known Activations