© 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. 66185
    Prev
    Next
    INDEX
    Explanations

    discovered findings

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

    The neuron is detecting numeric tokens (quantitative measurements or data values) 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
    茈
    -2.17
    刧
    -1.88
    ㆆ
    -1.86
     dédi
    -1.80
     пиво
    -1.76
    digans
    -1.76
    ехал
    -1.76
    幛
    -1.71
     bague
    -1.68
    圌
    -1.68
    POSITIVE LOGITS
     there
    2.55
    ↵
    2.28
     because
    2.14
    :
    2.09
    お金
    1.91
     be
    1.85
    *
    1.74
     as
    1.71
     preparada
    1.67
    ＞＞
    1.66
    Activations Density 0.058%

    No Known Activations