© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2709
    Prev
    Next
    INDEX
    Explanations

    demographic factors and trends

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

    The neuron responds to dense, fact‐laden passages that include specific details—especially numeric measurements, units, dates, names, and technical specifications.

    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
    🤭
    0.89
    🥴
    0.88
     tiktok
    0.88
    🥺
    0.87
     TikTok
    0.86
     covid
    0.85
    🥲
    0.80
    🥰
    0.80
     childish
    0.78
     Tiktok
    0.78
    POSITIVE LOGITS
     urbanization
    0.73
    보다는
    0.67
    Golf
    0.67
     경영
    0.67
     geographies
    0.66
     ਅਤੇ
    0.64
     outperforms
    0.63
    லுடன்
    0.63
     xrange
    0.63
    optimized
    0.63
    Activations Density 1.655%

    No Known Activations