© 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. 15724
    Prev
    Next
    INDEX
    Explanations

    iconic sights or landmarks

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

    The neuron activates on numeric expressions—quantities, measurements, statistics, distances, percentages, etc.

    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
    $
    0.77
    jet
    0.75
    inas
    0.73
    iap
    0.73
    icle
    0.72
    pert
    0.71
    0.71
    ario
    0.71
    z
    0.70
    gan
    0.70
    POSITIVE LOGITS
    า
    1.02
     estradiol
    1.00
     USAID
    0.99
     catalase
    0.99
     principalColumn
    0.99
     FISA
    0.99
     matriline
    0.98
     erad
    0.98
     Akshay
    0.98
     IAEA
    0.98
    Activations Density 0.001%

    No Known Activations