© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76257
    Prev
    Next
    INDEX
    Explanations

    monarchs and their reigns

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

    The neuron fires on formal titles of state office–holders (especially monarchical titles like “Monarch,” “Queen,” “Elizabeth II,” “Governor–General,” “Premier,” etc.).

    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
    ūsų
    -0.83
    Minister
    -0.80
    weł
    -0.76
    睹
    -0.75
     狼
    -0.73
     minister
    -0.72
    getContext
    -0.72
    merzen
    -0.71
     Ministerial
    -0.71
    paf
    -0.71
    POSITIVE LOGITS
     Queen
    1.09
     reigned
    1.07
     reign
    1.05
    Queen
    1.03
    👑
    1.00
    queen
    0.97
     Defender
    0.95
    Defender
    0.93
     reigns
    0.92
    女王
    0.90
    Activations Density 0.030%

    No Known Activations