© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    numerical ranges or separators

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

    The neuron fires on multi‐digit numeric tokens—particularly years, dates, measurements, or other numbers.

    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
     grandiose
    0.58
    цева
    0.50
     ਇਕ
    0.49
    ැන
    0.49
     oliva
    0.49
    Shoot
    0.48
    喋
    0.48
     Twice
    0.47
     meget
    0.47
     fourn
    0.47
    POSITIVE LOGITS
     έως
    1.27
     hingga
    1.23
     đến
    1.18
     till
    1.08
     إلى
    1.06
     onwards
    1.05
    到
    1.05
     až
    1.02
    至
    1.02
     الى
    1.01
    Activations Density 0.256%

    No Known Activations