© 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. 34-GEMMASCOPE-RES-131K
    7. 78859
    Prev
    Next
    INDEX
    Explanations

    Fort Lauderdale, Florida cities

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

    The neuron is specialized in spotting numeric tokens—especially multi‐digit numbers such as years, room or street numbers, and legal or case citations.

    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
    idious
    -0.76
    谅
    -0.74
    忘れて
    -0.70
    Kyoto
    -0.70
     DIFFERENT
    -0.68
     rejoint
    -0.67
    離
    -0.65
     lesen
    -0.64
     valenci
    -0.64
    尷
    -0.64
    POSITIVE LOGITS
     Broward
    1.87
     Lauderdale
    1.20
    Brow
    1.20
     Pembroke
    1.17
     Lauder
    0.99
     Everglades
    0.98
    Pem
    0.94
     Davie
    0.94
    CFU
    0.88
     Coral
    0.86
    Activations Density 0.031%

    No Known Activations