© 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. 6902
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric values (especially decimal or large numbers) 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
     spat
    0.71
     leta
    0.71
     serendip
    0.71
     unripe
    0.70
     a
    0.68
     gare
    0.66
    varez
    0.64
     the
    0.64
     dawn
    0.64
     incom
    0.64
    POSITIVE LOGITS
     항상
    0.68
     സഞ്ച
    0.67
     সবসময়
    0.67
    ActionButton
    0.66
    ListView
    0.65
    પ
    0.64
    ﻞ
    0.64
    ы
    0.63
    த்திற்கு
    0.63
     Evaluations
    0.62
    Activations Density 0.000%

    No Known Activations