© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4993
    Prev
    Next
    INDEX
    Explanations

    The neuron flags named entities—proper nouns like people’s names, places, and organizations.

    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
    槤
    0.89
    였
    0.82
    ऐसे
    0.81
    आइ
    0.78
    seems
    0.76
     encapsulate
    0.75
    thirty
    0.73
     podendo
    0.73
    了起来
    0.72
     đầy
    0.72
    POSITIVE LOGITS
    ﺭ
    0.81
    swering
    0.76
     обуча
    0.76
    ̵
    0.76
     Министерство
    0.76
    ﺩ
    0.74
    ATIONAL
    0.73
     Educ
    0.71
    ਗ
    0.70
    вач
    0.69
    Activations Density 0.000%

    No Known Activations