© 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. 9565
    Prev
    Next
    INDEX
    Explanations

    Renaissance and Florence

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

    The neuron activates on historical‐context markers—especially dates, years, centuries, and named places or powers in history—flagging text that situates events in time.

    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
     Westinghouse
    0.68
    明治
    0.68
     emigrated
    0.63
     दादा
    0.61
     ১৯৭
    0.60
     소련
    0.60
     herd
    0.60
    酋
    0.60
     бара
    0.59
     Nagano
    0.59
    POSITIVE LOGITS
    Medieval
    1.55
     medieval
    1.49
     Medieval
    1.48
     Renaissance
    1.44
    medieval
    1.39
    Rena
    1.36
     fifteenth
    1.23
     Florent
    1.13
     Chaucer
    1.13
     Florence
    1.02
    Activations Density 0.174%

    No Known Activations