© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10025
    Prev
    Next
    INDEX
    Explanations

    hidden claim to power

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

    This neuron lights up on references to royalty, nobility, high‐status titles, and associated proper names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     налич
    0.57
     সমিতি
    0.54
     کولی
    0.54
    ycopg
    0.52
    宕
    0.52
    ູນ
    0.51
     Fossil
    0.51
     trồng
    0.51
     antiviral
    0.51
     Eastwood
    0.51
    POSITIVE LOGITS
     royal
    2.39
     royals
    2.28
     monarchs
    2.22
     monarch
    2.17
     monarchy
    2.11
     king
    2.03
     throne
    2.00
     kings
    1.99
    皇
    1.98
    royal
    1.96
    Activations Density 0.358%

    No Known Activations