© 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. 116810
    Prev
    Next
    INDEX
    Explanations

    patent numbers

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

    The neuron is activated by long sequences of digits (e.g. numerical identifiers like DOIs, patent numbers, years, or hex color codes).

    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
     ц
    -0.81
    匣
    -0.78
    sied
    -0.78
     Balo
    -0.73
    ンテ
    -0.72
    quite
    -0.72
    Ion
    -0.71
     QU
    -0.71
    analy
    -0.71
     sev
    -0.71
    POSITIVE LOGITS
     赵
    0.82
     its
    0.81
     shocking
    0.80
     unmöglich
    0.77
    edizione
    0.77
     tấm
    0.76
    стера
    0.76
    সূ
    0.75
     път
    0.75
     decreased
    0.74
    Activations Density 0.050%

    No Known Activations