© 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. 1116
    Prev
    Next
    INDEX
    Explanations

    The neuron is strongly activated by the subword sequence for the drug‐name phrase “Clomid And Cialis.”

    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
     the
    1.02
    the
    0.80
    을
    0.73
     The
    0.72
     and
    0.71
    ;
    0.70
     are
    0.68
     de
    0.67
    ,
    0.66
     has
    0.66
    POSITIVE LOGITS
    নারী
    0.77
    出来る
    0.73
    色々
    0.71
     こんな
    0.71
     কোথা
    0.70
     জীববিজ্ঞান
    0.70
    띵
    0.70
     みたい
    0.70
    
    0.69
     চরিত্র
    0.68
    Activations Density 0.008%

    No Known Activations