© 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. 73658
    Prev
    Next
    INDEX
    Explanations

    military academies and cadets

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

    The neuron activates on standalone numeric tokens (especially years and other multi‐digit numbers).

    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
     עבודה
    -0.78
     sheriff
    -0.77
     passport
    -0.75
    ggish
    -0.74
    ARROW
    -0.74
    tyg
    -0.72
    GED
    -0.71
     constitución
    -0.71
    DBC
    -0.69
    检
    -0.69
    POSITIVE LOGITS
     cadets
    1.26
     cadet
    1.13
     plebe
    1.12
     Cadet
    1.05
    Cade
    1.00
     Annapolis
    0.84
     Cade
    0.83
     academy
    0.78
    čen
    0.77
     mids
    0.76
    Activations Density 0.012%

    No Known Activations