© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    companies and people by nationality

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

    The neuron activates on nationality or demonym words (e.g. “British,” “German,” “Australian”) that describe a person’s origin.

    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
     Hogwarts
    0.65
     Sicilia
    0.65
     Ελλάδα
    0.63
    사각형
    0.61
    ockets
    0.60
     casks
    0.59
     대한민국
    0.59
    ש
    0.59
     каждой
    0.58
    igkeiten
    0.57
    POSITIVE LOGITS
     billionaire
    0.91
     filmmaker
    0.91
     businessman
    0.83
    businessman
    0.83
     teenager
    0.82
     politician
    0.81
     guitarist
    0.79
     veteran
    0.78
     singer
    0.77
     rapper
    0.77
    Activations Density 0.011%

    No Known Activations