© 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. 4517
    Prev
    Next
    INDEX
    Explanations

    f(x)

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

    The neuron is specialized in spotting numeric tokens—particularly age and date numbers—in obituary or death‐notice contexts.

    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
    શ
    0.61
     Advancement
    0.60
     ऐप्प
    0.60
    _${
    0.57
     Gunners
    0.55
     Shree
    0.55
    Archives
    0.54
    ອ
    0.53
     Waterfront
    0.53
     Reihen
    0.53
    POSITIVE LOGITS
    æt
    0.59
     เฟ
    0.57
    攻擊
    0.55
    াড়ি
    0.55
     предлага
    0.54
     menawarkan
    0.52
    遨
    0.52
     కూడా
    0.51
     देखील
    0.51
     fonksiyon
    0.51
    Activations Density 0.007%

    No Known Activations