© 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. 7865
    Prev
    Next
    INDEX
    Explanations

    Bruschetta, a type of appetizer

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

    The neuron fires on content words used as labels or headings in structured listings—e.g. schedule slots (morning, afternoon, sessions, days), figure‐panel or section descriptors (design, inactive, left, active, right), and other technical or “term” labels (networks, momentum, office space, handy).

    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
     samoch
    0.87
     ήταν
    0.86
     был
    0.84
     фильм
    0.82
     reembolso
    0.82
     pembayaran
    0.82
     również
    0.78
     entretenimiento
    0.77
     слегка
    0.77
     انہوں
    0.77
    POSITIVE LOGITS
    cbind
    0.68
    rbind
    0.66
    Includes
    0.63
    Data
    0.63
     basics
    0.63
    with
    0.62
    sys
    0.62
    context
    0.61
    किस
    0.61
    class
    0.60
    Activations Density 0.088%

    No Known Activations