© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14987
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to named entities—proper nouns such as country names, organizations, event titles, and place names.

    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
    нути
    0.61
     $[-
    0.60
     $(\
    0.59
     laterally
    0.58
     narcot
    0.58
     samma
    0.57
    aissez
    0.57
    잖아요
    0.56
     $,
    0.54
     Mugabe
    0.54
    POSITIVE LOGITS
     sketchbook
    0.77
     treatise
    0.72
    Czech
    0.70
     తన
    0.69
    schrift
    0.69
    atelier
    0.69
    Ბ
    0.67
    М
    0.67
    Л
    0.67
     своего
    0.66
    Activations Density 0.980%

    No Known Activations