© 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. 9065
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on named entities—proper names of people, places, organizations, dates, etc.

    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
     caregivers
    0.88
    silyl
    0.87
     compartilhar
    0.81
    βάλ
    0.80
    ]->
    0.79
     kapcsol
    0.79
     Pleistocene
    0.78
     qualifiers
    0.78
     Defendants
    0.77
     Exceptions
    0.72
    POSITIVE LOGITS
     superb
    0.70
    ’
    0.67
     superbly
    0.67
     ומ
    0.66
    Cele
    0.64
    Автор
    0.64
     видим
    0.62
    .’
    0.61
    arni
    0.60
     ari
    0.60
    Activations Density 0.000%

    No Known Activations