© 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. 7983
    Prev
    Next
    INDEX
    Explanations

    The neuron fires primarily on floating‐point numeric tokens (decimal numbers), such as those in DOIs, page ranges, or volume/year citations.

    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
    ik
    0.90
     c
    0.75
     d
    0.74
     చెందిన
    0.72
    ans
    0.71
     old
    0.71
     previous
    0.70
       
    0.70
     a
    0.70
     initialize
    0.70
    POSITIVE LOGITS
    IRCONIUM
    0.87
    ství
    0.81
    ORES
    0.80
    ATORS
    0.77
     увагу
    0.76
    HEMAT
    0.75
    किस्तान
    0.75
    ığım
    0.75
    LEMN
    0.75
    UCLE
    0.74
    Activations Density 0.001%

    No Known Activations