© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74183
    Prev
    Next
    INDEX
    Explanations

    product codes or model numbers

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

    The neuron fires on numeric tokens—that is, 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
     in
    -1.92
     by
    -1.91
     would
    -1.76
     \&
    -1.68
    大半
    -1.62
     could
    -1.56
    裏面
    -1.55
    神器
    -1.55
    ùn
    -1.52
     with
    -1.52
    POSITIVE LOGITS
    我們
    1.91
     hva
    1.74
    我们
    1.74
     hebt
    1.63
    länd
    1.59
     mede
    1.57
     avantage
    1.56
     İş
    1.55
    mbres
    1.53
    ₤
    1.53
    Activations Density 0.094%

    No Known Activations