© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2644
    Prev
    Next
    INDEX
    Explanations

    Buenos Aires

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

    The neuron fires strongly on mentions of pharmaceutical drug names (especially erectile-dysfunction drugs like Viagra, Cialis, Clomid, Levitra, etc.) and their dosages.

    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
    фра
    0.42
    irse
    0.37
    Biology
    0.35
    ቬ
    0.35
    College
    0.35
     কৃষি
    0.34
    ©
    0.33
    Bi
    0.33
    পদার্থ
    0.33
    طلب
    0.33
    POSITIVE LOGITS
     Margherita
    0.36
     Tanger
    0.35
     switcher
    0.35
     schwe
    0.35
     rug
    0.35
     Blueberry
    0.35
     Alpen
    0.34
    eneuve
    0.34
     QP
    0.34
     clang
    0.34
    Activations Density 0.037%

    No Known Activations