© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15916
    Prev
    Next
    INDEX
    Explanations

    United States, Kingdom, Nations

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

    The neuron activates on occurrences of the term “United” when used in major multi‐word named entities (e.g. “United Nations,” “United States”).

    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
     tī
    0.54
     aest
    0.54
    就可以
    0.53
    จร
    0.53
     leech
    0.53
    哟
    0.53
     natuurlijk
    0.53
     pericard
    0.53
     urn
    0.52
    關
    0.52
    POSITIVE LOGITS
     Nations
    0.93
     States
    0.86
     Kingdom
    0.85
     STATES
    0.80
    Kingdom
    0.78
    States
    0.76
     Königreich
    0.76
     фрон
    0.74
     Kingdoms
    0.73
    王国
    0.70
    Activations Density 0.137%

    No Known Activations