© 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. 24-GEMMASCOPE-2-RES-16K
    4. 6682
    Prev
    Next
    INDEX
    Explanations

    US and British diplomatic actions

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

    The neuron selectively activates on occurrences of the abbreviation “US” (or “U.S.”) referring to the 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_24_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
     troublesome
    0.57
     boxe
    0.54
     Nippon
    0.52
     Sasuke
    0.51
    
    0.51
     Pareto
    0.50
     IAAF
    0.49
    ,]$
    0.49
    Type
    0.48
    ={'
    0.48
    POSITIVE LOGITS
     envoy
    0.64
     embassy
    0.60
    loans
    0.60
    umbria
    0.60
     मिशन
    0.58
    military
    0.58
    ങ്ങാ
    0.57
    rod
    0.57
     ಅಗತ್ಯ
    0.56
    munition
    0.56
    Activations Density 0.001%

    No Known Activations