© 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. 14239
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on prominent content-bearing nouns or technical jargon—specialized terms that serve as headings or key domain-specific keywords.

    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
     or
    0.70
     Time
    0.68
     Consultado
    0.65
     Zuma
    0.64
     Auss
    0.63
    Timeout
    0.63
     :
    0.62
    ,
    0.62
     Zy
    0.61
     Holden
    0.61
    POSITIVE LOGITS
    自身の
    0.72
    自身的
    0.71
    écies
    0.70
     자체가
    0.66
     dextrose
    0.66
     Tattha
    0.65
    自身
    0.63
     paradig
    0.61
    本身的
    0.61
     തന്നെ
    0.61
    Activations Density 0.000%

    No Known Activations