© 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. 59898
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    The neuron is primarily detecting numeric tokens—digits or numbers (e.g. multi‐digit values, counts, dates, statistics) 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
     five
    -1.84
     four
    -1.70
     six
    -1.66
     three
    -1.46
    five
    -1.41
     seven
    -1.34
     two
    -1.30
    Five
    -1.30
    three
    -1.21
    Three
    -1.18
    POSITIVE LOGITS
     twenty
    1.80
     Twenty
    1.68
    Twenty
    1.57
     Thirty
    1.55
    Thirty
    1.49
     thirty
    1.48
    二十
    1.47
    twenty
    1.35
     TWENTY
    1.28
     nineteen
    1.21
    Activations Density 0.121%

    No Known Activations