© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of “pills,” especially in contexts like diet or supplement pills.

    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
     ال
    0.59
     Π
    0.57
     ブ
    0.56
    ֑
    0.55
    vib
    0.54
    also
    0.54
     Также
    0.53
     サ
    0.53
     Also
    0.52
     также
    0.52
    POSITIVE LOGITS
     XIX
    0.60
     vucc
    0.59
    숑
    0.59
     polygonal
    0.58
     institucional
    0.58
     तत्वा
    0.57
     edição
    0.57
    뀜
    0.56
    몄
    0.56
     punctato
    0.55
    Activations Density 0.000%

    No Known Activations