© 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. 16194
    Prev
    Next
    INDEX
    Explanations

    Arabic, Islam, Quran

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

    This neuron activates strongly on named entities—proper nouns referring to people, places, organizations, and similar entities.

    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
    푥
    0.87
     obsess
    0.84
    푦
    0.82
     quirks
    0.81
    뒤
    0.79
     looming
    0.76
    푎
    0.76
    을
    0.76
    mathrm
    0.75
    그램
    0.75
    POSITIVE LOGITS
     Baloch
    1.59
     Islamabad
    1.55
     Yemeni
    1.48
     Quran
    1.46
     Mohammad
    1.45
     Mubarak
    1.41
     Sindh
    1.41
     Tajik
    1.38
     Masjid
    1.36
     Shahid
    1.34
    Activations Density 1.294%

    No Known Activations