© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7163
    Prev
    Next
    INDEX
    Explanations

    capacity, percentage, stocks, exercise, stress, contractors

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

    The neuron strongly activates on nouns in their plural or collective form (e.g. “Republicans,” “engines,” “auctions,” “costs”).

    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
     fintech
    1.19
     🥰
    1.14
     Fintech
    1.09
     underpinned
    1.04
    🤭
    1.03
     telecoms
    1.02
     metaverse
    0.97
     blockchains
    0.96
    constexpr
    0.96
     Sunak
    0.95
    POSITIVE LOGITS
    .
    0.83
    或者是
    0.79
    http
    0.79
     Greeley
    0.77
     অথবা
    0.77
    Pittsburgh
    0.75
     heretofore
    0.75
     Redskins
    0.75
    Ã
    0.75
     Sandusky
    0.74
    Activations Density 0.157%

    No Known Activations