© 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. 16137
    Prev
    Next
    INDEX
    Explanations

    French or equation context

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

    The neuron detects occurrences of the German word “Bücher” (i.e. “books”) in download or online‐reading link 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
    _*
    0.81
     خواتین
    0.72
    〟
    0.70
    ׂ
    0.70
    椀
    0.69
     મહિલા
    0.68
     മുതല്‍
    0.66
     знаю
    0.66
    raron
    0.65
     системой
    0.64
    POSITIVE LOGITS
     Allergy
    0.70
    ابس
    0.67
     colds
    0.66
     svært
    0.65
     transplantation
    0.64
     hydrox
    0.64
     Infection
    0.63
     Elf
    0.62
     cts
    0.61
    鲟
    0.61
    Activations Density 0.000%

    No Known Activations