© 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. 22-GEMMASCOPE-RES-131K
    7. 73794
    Prev
    Next
    INDEX
    Explanations

    initial stages of things

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

    The neuron responds to numeric or quantitative tokens—years, centuries, percentages, measurements, and other numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     آخر
    -1.14
    Outro
    -1.03
    最后一个
    -1.02
     última
    -0.99
     akhir
    -0.98
    final
    -0.98
     eof
    -0.94
     послед
    -0.93
    最後の
    -0.93
    最後
    -0.92
    POSITIVE LOGITS
     beginning
    2.63
     early
    2.61
     first
    2.59
     starting
    2.58
     initial
    2.42
     start
    2.33
     begins
    2.27
    เริ่ม
    2.27
     begin
    2.20
     первые
    2.09
    Activations Density 0.215%

    No Known Activations