© 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. 111009
    Prev
    Next
    INDEX
    Explanations

    career roles and achievements

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

    The neuron detects numeric and quantitative tokens—especially years, dates, and numerical measures—within biographical 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
     other
    -2.13
     أخرى
    -1.38
     they
    -1.37
     by
    -1.32
     themselves
    -1.14
     presidenta
    -1.14
    其他
    -1.13
     eachother
    -1.12
     tighter
    -1.12
     altre
    -1.11
    POSITIVE LOGITS
     tiež
    1.41
     además
    1.41
     cũng
    1.36
     även
    1.30
    ๛
    1.27
     alſo
    1.26
     materiál
    1.26
    :{
    1.25
     rých
    1.25
    ึกษา
    1.24
    Activations Density 0.131%

    No Known Activations