© 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. 5047
    Prev
    Next
    INDEX
    Explanations

    function parameters or types

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

    The neuron fires strongly on “weird” subword tokens—things like raw numbers (e.g. “7”), URL fragments (e.g. “com/”), and other non-standard word pieces—i.e. it spots tokens containing digits or punctuation rather than ordinary words.

    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
     p
    0.81
     siden
    0.81
    fasst
    0.77
     data
    0.75
    s
    0.71
    empel
    0.69
    യും
    0.67
     bid
    0.65
     vemos
    0.64
    かせ
    0.64
    POSITIVE LOGITS
     oreilles
    0.94
     Yeon
    0.92
     Ні
    0.92
     DAB
    0.89
     💞
    0.87
     🌱
    0.87
     Ubuy
    0.86
     Witcher
    0.85
    🙎
    0.85
     Đức
    0.84
    Activations Density 0.001%

    No Known Activations