© 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. 11387
    Prev
    Next
    INDEX
    Explanations

    regular scheduled checks

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

    The neuron fires on numeric data—especially floating‐point or statistical figures—when they appear in the text.

    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
    ни
    0.91
     distinguished
    0.78
     pronounced
    0.78
    0.77
     assum
    0.77
     don
    0.75
    INE
    0.74
     對
    0.73
     démont
    0.73
     omitted
    0.70
    POSITIVE LOGITS
     Опреде
    0.90
    枭
    0.86
     buildTypes
    0.83
     срока
    0.83
     merken
    0.80
    ೨
    0.80
    peliculas
    0.80
    垪
    0.79
     Puedes
    0.79
    係る
    0.79
    Activations Density 0.002%

    No Known Activations