© 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. 84105
    Prev
    Next
    INDEX
    Explanations

    specific identifying information

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

    The neuron strongly activates on numeric tokens—digits, decimal numbers, and numerical ratings or quantities.

    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
     Amazon
    -1.21
    Amazon
    -1.20
    亚马逊
    -1.13
     AMAZON
    -1.07
     amazon
    -1.02
    amazon
    -1.02
    AMAZ
    -0.95
     Kindle
    -0.89
     Bezos
    -0.88
     امروز
    -0.83
    POSITIVE LOGITS
    actéristiques
    0.98
     purchased
    0.95
     #
    0.95
     bought
    0.95
    nagem
    0.89
     product
    0.88
    лення
    0.85
     purchases
    0.84
    :'#
    0.80
    uned
    0.80
    Activations Density 0.010%

    No Known Activations