© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11187
    Prev
    Next
    INDEX
    Explanations

    Nikola Tesla, Nissan, Nishat

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

    The neuron responds to capitalized proper nouns—names of people, places, or other named 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_31_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
     Certains
    0.57
     quedaron
    0.55
    燵
    0.55
     paraphrase
    0.55
     Beaucoup
    0.54
     Então
    0.54
    recursive
    0.54
    ριο
    0.54
     Globo
    0.53
    ным
    0.53
    POSITIVE LOGITS
     ニ
    0.86
     นิ
    0.79
    Nickel
    0.79
    odeon
    0.76
     Nickel
    0.73
     NIC
    0.73
     Nic
    0.69
     니
    0.67
    Nick
    0.66
    Nic
    0.65
    Activations Density 0.160%

    No Known Activations