© 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. 32869
    Prev
    Next
    INDEX
    Explanations

    military supply depots

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

    The neuron is specialized in spotting numeric tokens—especially multi‐digit numbers and dates—in a document.

    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
    pew
    -0.80
    愛
    -0.73
     Flying
    -0.71
    wies
    -0.71
    bier
    -0.71
     stället
    -0.71
     Subjects
    -0.70
    டிய
    -0.69
    lové
    -0.69
    adz
    -0.69
    POSITIVE LOGITS
     depot
    1.07
     soutien
    1.04
     depots
    0.95
     warehouses
    0.86
     arsen
    0.85
     supply
    0.80
     repair
    0.79
     Depot
    0.78
     скла
    0.77
     purchasing
    0.76
    Activations Density 0.023%

    No Known Activations