© 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. 524
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on standalone numeric tokens (especially decimal numbers).

    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
     nonce
    0.27
    ะนั้น
    0.25
    ソース
    0.25
     embodiment
    0.24
    ก็ได้
    0.24
     embodiments
    0.24
     (/
    0.24
    ↓
    0.24
    เลข
    0.23
    ルール
    0.23
    POSITIVE LOGITS
     Meskipun
    0.40
     apesar
    0.39
     Apesar
    0.38
     Despite
    0.37
     我們
    0.37
     भयानक
    0.37
    🇬
    0.36
     안녕하세요
    0.36
     虽然
    0.36
     我们
    0.36
    Activations Density 0.198%

    No Known Activations