© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words and tokens that signal age or vintage—e.g. “old,” “ancient,” year numbers, and other historical/time‐period markers.

    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
    餃
    0.84
     agregado
    0.81
     watermelon
    0.79
     nameWithOwner
    0.78
    स
    0.78
    𝘇
    0.78
    bumper
    0.77
     بیمار
    0.77
     vuelos
    0.77
     melon
    0.76
    POSITIVE LOGITS
    ancient
    1.70
     antiquity
    1.64
     centuries
    1.63
     ancient
    1.53
     древ
    1.52
    古
    1.48
     xưa
    1.48
    Ancient
    1.45
     Ancient
    1.41
     প্রাচীন
    1.41
    Activations Density 2.101%

    No Known Activations