© 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. 11919
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly lights up on open‐class “content” words—nouns, verbs, gerunds, etc.—rather than on function words.

    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
    ל
    0.89
    {
    0.88
    い
    0.87
    بر
    0.82
    ก
    0.81
    L
    0.80
    વ
    0.79
    l
    0.78
    Ook
    0.77
    র্ব
    0.74
    POSITIVE LOGITS
     Букмекерская
    0.71
     stør
    0.70
    adó
    0.70
    ashmir
    0.70
     मूव
    0.70
     Пользова
    0.69
    ELER
    0.66
     防止
    0.66
    °-
    0.66
     Анти
    0.65
    Activations Density 0.000%

    No Known Activations