© 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. 5378
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the first (capitalized) word of each numbered program or workshop title in the listing.

    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
    LJ
    0.79
    膽
    0.75
    B
    0.74
    L
    0.73
     Reliable
    0.72
     nörd
    0.72
     nuov
    0.70
    ܘܢ
    0.70
    H
    0.70
     जॉ
    0.69
    POSITIVE LOGITS
     Такой
    0.93
    ᅠ
    0.80
    יות
    0.77
    ्स
    0.71
    вання
    0.71
    sof
    0.71
    ษา
    0.69
     حق
    0.68
    िया
    0.68
    רט
    0.68
    Activations Density 0.000%

    No Known Activations