© 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. 116870
    Prev
    Next
    INDEX
    Explanations

    South Carolina | Jr. | Carver Elementary

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

    This neuron activates on numeric tokens—digits, numeric codes, measurements, and other number-like strings.

    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
    香港
    -0.77
     Unters
    -0.75
    天
    -0.75
    pão
    -0.74
    apte
    -0.74
    डे
    -0.74
    在
    -0.72
    tume
    -0.71
    하
    -0.70
    Hong
    -0.69
    POSITIVE LOGITS
     Myrtle
    0.99
    Conway
    0.94
    inkite
    0.93
    Myr
    0.92
     Conway
    0.88
    ampunk
    0.84
     Dunes
    0.83
     Phong
    0.82
    Strand
    0.81
     RICE
    0.81
    Activations Density 0.009%

    No Known Activations