© 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. 69253
    Prev
    Next
    INDEX
    Explanations

    famous retired figures

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

    The neuron fires strongly on capitalized personal names—especially surnames of well-known individuals.

    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
    小时候
    -1.17
     немного
    -1.13
    :
    -1.13
     \
    -1.10
     $
    -1.04
     я
    -1.01
     them
    -0.97
     =
    -0.96
    ñó
    -0.96
    ùng
    -0.95
    POSITIVE LOGITS
     retired
    1.95
    retired
    1.73
     retirement
    1.73
     elderly
    1.55
     octo
    1.51
     emeritus
    1.51
     decades
    1.50
     Retired
    1.47
     Emeritus
    1.46
     veteran
    1.45
    Activations Density 0.127%

    No Known Activations