© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62747
    Prev
    Next
    INDEX
    Explanations

    dynastic succession and ruling houses

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

    The neuron is tuned to pick up mentions of dynastic lineage, “dynasty,” and “dynastic” (and related succession terminology).

    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
    льти
    -0.75
     workforce
    -0.73
     associations
    -0.72
     Tuchel
    -0.70
    nium
    -0.68
     citta
    -0.68
    tování
    -0.66
    稟
    -0.66
     ganzen
    -0.66
     treatments
    -0.65
    POSITIVE LOGITS
     dynasty
    3.09
     Dynasty
    2.48
     dyn
    2.33
     dynasties
    2.19
    dyna
    2.00
    dyn
    1.86
    Dyna
    1.78
     dyna
    1.71
     Dyn
    1.69
    王朝
    1.59
    Activations Density 0.056%

    No Known Activations