© 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. 13045
    Prev
    Next
    INDEX
    Explanations

    This neuron detects named entities and other specific proper nouns or titles in the text.

    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
     político
    0.81
     secretaria
    0.80
     verá
    0.80
     administrativo
    0.79
     สุด
    0.79
     ########.
    0.78
     músico
    0.78
    ედერ
    0.77
     debía
    0.77
     願い
    0.77
    POSITIVE LOGITS
     appet
    0.83
    s
    0.80
    het
    0.74
    println
    0.73
    agen
    0.73
    me
    0.73
    hap
    0.71
    uss
    0.70
    ться
    0.70
    appearance
    0.68
    Activations Density 0.001%

    No Known Activations