© 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. 81251
    Prev
    Next
    INDEX
    Explanations

    US states and cities

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

    This neuron specializes in spotting numeric tokens (multi‐digit numbers such as years, measurements, addresses, or statistics).

    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
    ayet
    -0.91
    是什么意思
    -0.76
    هة
    -0.73
     NEGRO
    -0.73
    ྔ
    -0.72
    HTTPClient
    -0.72
    ГЛА
    -0.71
    wm
    -0.70
     Guill
    -0.69
    Magnolia
    -0.69
    POSITIVE LOGITS
     Billings
    1.13
     Yellowstone
    1.12
    Yellow
    0.90
     Cody
    0.79
     المص
    0.74
     Yellow
    0.74
     Scar
    0.73
     entrar
    0.73
     yellows
    0.69
     Pf
    0.69
    Activations Density 0.011%

    No Known Activations