© 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. 20526
    Prev
    Next
    INDEX
    Explanations

    number of

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

    The neuron strongly activates on numeric expressions—especially occurrences of the word “number” followed by or associated with digits—i.e. mentions of counts or measured 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_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
    [
    -2.20
    ”
    -1.77
     extent
    -1.75
    ↵↵
    -1.66
    ]
    -1.65
    (
    -1.57
     enormous
    -1.50
     what
    -1.49
    -
    -1.45
     both
    -1.44
    POSITIVE LOGITS
    禔
    1.77
    侂
    1.66
    轵
    1.62
    demás
    1.58
    睒
    1.57
    𐍃
    1.56
    Ⓩ
    1.55
    ÍAS
    1.54
     Ответить
    1.53
    ！");
    1.52
    Activations Density 0.219%

    No Known Activations