© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14645
    Prev
    Next
    INDEX
    Explanations

    present a, that cancer, works in

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

    The neuron consistently lights up on numeric tokens—years, statistics, percentages, and 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
    1
    1.06
    (
    1.02
    !
    1.00
     (
    0.94
     NCBI
    0.94
    /
    0.92
    UI
    0.91
    I
    0.91
    7
    0.91
    0.89
    POSITIVE LOGITS
     sprawling
    1.31
     dogged
    1.15
     কার্যত
    1.12
     राजनीतिक
    1.06
     deftly
    1.06
     सियासी
    1.06
     паліты
    1.05
     geopol
    1.05
     tumult
    1.04
     политика
    1.04
    Activations Density 0.416%

    No Known Activations