© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3882
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on passages describing U.S. power, foreign policy, or imperial/geopolitical conflicts.

    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
     sekä
    0.70
     sämt
    0.70
    టువంటి
    0.68
     valamint
    0.68
     以及
    0.67
     تمامی
    0.67
     ،
    0.65
    وو
    0.65
     oraz
    0.64
    それでは
    0.64
    POSITIVE LOGITS
    未必
    0.89
     võivad
    0.87
     може
    0.75
     могут
    0.75
     অনেকে
    0.72
     можуть
    0.72
     могли
    0.71
     mogą
    0.70
     może
    0.69
     mohou
    0.67
    Activations Density 0.070%

    No Known Activations