© 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. 10-GEMMASCOPE-RES-131K
    7. 39139
    Prev
    Next
    INDEX
    Explanations

    that

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

    The neuron activates on numerical expressions (digits or numbers) 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_10/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
    l
    -1.78
     Nonetheless
    -1.70
    ть
    -1.65
     feststellen
    -1.64
    或
    -1.63
    ла
    -1.61
    u
    -1.55
    os
    -1.54
     Nevertheless
    -1.52
    喔
    -1.51
    POSITIVE LOGITS
     this
    2.08
     there
    2.08
     ४
    1.87
     with
    1.82
    眥
    1.76
     now
    1.75
     into
    1.73
     without
    1.70
     while
    1.66
     doba
    1.59
    Activations Density 0.149%

    No Known Activations