© 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. 31-GEMMASCOPE-2-RES-16K
    7. 615
    Prev
    Next
    INDEX
    Explanations

    & and

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

    This neuron detects the ampersand character (“&”).

    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
    ть
    0.55
    －－
    0.55
    ﹁
    0.55
    NaN
    0.54
    却
    0.54
    
    0.53
    乃至
    0.52
    
    0.52
    🪙
    0.52
    卻
    0.51
    POSITIVE LOGITS
    amp
    0.91
    ndash
    0.69
     Partners
    0.68
     Friends
    0.66
     Associates
    0.63
     ehemal
    0.61
     partners
    0.61
     Society
    0.59
     amp
    0.59
     Related
    0.58
    Activations Density 0.388%

    No Known Activations