© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44301
    Prev
    Next
    INDEX
    Explanations

    military officer designations

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

    The main thing this neuron does is detect mentions of military ranks and officer titles.

    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
     vengan
    -1.79
     někter
    -1.70
    selben
    -1.58
     nasze
    -1.55
     enseñ
    -1.52
     lämp
    -1.48
    𝐌
    -1.47
    錀
    -1.47
     รี
    -1.47
     recrutement
    -1.46
    POSITIVE LOGITS
     will
    1.38
    ValueGeneration
    1.31
     और
    1.31
    ！』
    1.30
     disregard
    1.30
     has
    1.30
     may
    1.30
     القديمة
    1.30
    !*\
    1.30
     certainly
    1.29
    Activations Density 0.024%

    No Known Activations