© 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. 7510
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of organizations or associations (e.g. proper-name group titles like “Surface Navy Association”).

    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
     unconventional
    0.76
    搭载
    0.71
     effectuées
    0.67
    劇場
    0.66
     場所
    0.66
     vollständig
    0.66
     orchestration
    0.66
    櫒
    0.65
    شت
    0.65
     intención
    0.64
    POSITIVE LOGITS
    会员
    1.22
    association
    1.19
    membership
    1.16
     membership
    1.15
    Association
    1.13
    會員
    1.13
     members
    1.10
     Membership
    1.09
    Membership
    1.09
     MEMBERS
    1.08
    Activations Density 0.979%

    No Known Activations