© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15899
    Prev
    Next
    INDEX
    Explanations

    Here's the

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

    The neuron fires on descriptions of decorative lighting installations (e.g. fairy lights, chandeliers, festoon canopies) used to adorn venues.

    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
    THING
    0.69
     español
    0.66
     bilhões
    0.65
     çünkü
    0.65
    ↵
    0.61
     schließlich
    0.61
    ერის
    0.61
     joka
    0.60
     meskipun
    0.60
     artikkel
    0.60
    POSITIVE LOGITS
    ="))
    0.63
    there
    0.57
    extré
    0.55
    परेटर
    0.55
    zyma
    0.54
    клады
    0.53
    cido
    0.51
    ль
    0.51
    plicate
    0.50
    chloride
    0.50
    Activations Density 0.729%

    No Known Activations