© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4698
    Prev
    Next
    INDEX
    Explanations

    books titles or names

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

    The neuron specifically activates on the word “International,” flagging occurrences of that token (e.g., in names like “International Airport”).

    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
     چې
    0.68
     Józ
    0.66
     بابەت
    0.65
     संघटने
    0.64
     माजी
    0.61
     ktorí
    0.61
    骜
    0.61
     tjän
    0.61
     abiert
    0.60
     którzy
    0.60
    POSITIVE LOGITS
     PowerPoint
    0.75
     to
    0.73
     in
    0.69
     മറ്റ്
    0.65
     Life
    0.63
     エ
    0.63
     SharePoint
    0.62
     for
    0.62
     Landscape
    0.61
     GPS
    0.61
    Activations Density 0.000%

    No Known Activations