© 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. 70235
    Prev
    Next
    INDEX
    Explanations

    military and police ranks

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

    The neuron is activated by military rank abbreviations or titles (e.g. “Flt Lt,” “Staff Sergeant,” “Rear Admiral,” etc.).

    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
     gitar
    -0.82
     sette
    -0.81
    Faker
    -0.80
     personne
    -0.79
    tomic
    -0.77
     mannen
    -0.76
    cuterie
    -0.76
     اللح
    -0.75
     TestCase
    -0.75
     animali
    -0.75
    POSITIVE LOGITS
     Sergeant
    1.44
     sergeant
    1.40
     Sgt
    1.30
     Leader
    1.30
     Commander
    1.15
     leader
    1.08
     commander
    1.04
    Sgt
    1.03
    Sergeant
    0.98
    Leader
    0.95
    Activations Density 0.045%

    No Known Activations