© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

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

    The neuron identifies numeric tokens—especially decimal numbers and measurement values—throughout 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
    ↵↵
    -2.16
    the
    -1.95
    bundet
    -1.93
     decorativos
    -1.88
    +}\
    -1.85
    两人的
    -1.83
     ”
    -1.80
    渼
    -1.79
    鱉
    -1.78
    悽
    -1.77
    POSITIVE LOGITS
    2
    2.06
    其他
    2.05
    蔬
    1.91
    5
    1.87
    er
    1.84
    但我
    1.77
    这一
    1.77
    //
    1.75
    4
    1.74
     cowok
    1.72
    Activations Density 0.008%

    No Known Activations