© 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. 10057
    Prev
    Next
    INDEX
    Explanations

    options, weights, locations, best

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

    The neuron is a high‐gain detector for numeric/statistical contexts—i.e. it fires strongly on tokens that are part of or immediately follow numerical data or quantitative figures.

    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
    г
    1.13
    Да
    1.08
    К
    1.07
    со
    1.03
    бе
    1.02
    О
    1.01
    о
    0.99
    Се
    0.96
    ко
    0.95
    Со
    0.95
    POSITIVE LOGITS
     Pendidikan
    0.92
     kayaking
    0.91
     nugget
    0.91
     cortical
    0.90
     phylogeny
    0.87
     cytotoxic
    0.85
     deoxy
    0.85
     aloe
    0.84
     Kurdish
    0.84
     UNIX
    0.83
    Activations Density 0.030%

    No Known Activations