© 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. 84335
    Prev
    Next
    INDEX
    Explanations

    age in years

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

    The neuron strongly activates on numeric tokens (digits) in the text.

    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
     more
    -1.27
    Бы
    -1.03
     now
    -1.01
    Fifty
    -0.99
    gill
    -0.97
    瑜伽
    -0.92
     более
    -0.91
     medio
    -0.88
    Hundreds
    -0.88
    рного
    -0.86
    POSITIVE LOGITS
     eight
    1.30
     five
    1.29
     seven
    1.18
    five
    1.09
     nine
    1.09
     four
    1.02
     six
    1.02
     toddler
    1.02
     küçük
    1.00
    knee
    0.95
    Activations Density 0.034%

    No Known Activations