© 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. 84
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on numeric tokens—especially multi‐digit or decimal numbers denoting measurements or quantities.

    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
    0.40
    2
    0.33
    :
    0.32
    1
    0.30
    ?
    0.28
     and
    0.28
    _
    0.27
    3
    0.27
    -
    0.26
            
    0.26
    POSITIVE LOGITS
     thậm
    0.32
     equivalently
    0.29
     ఇతర
    0.29
     whatnot
    0.29
     lihtsalt
    0.28
     अन्य
    0.28
     akár
    0.28
    逆に
    0.27
    ख्ती
    0.27
     اینکه
    0.26
    Activations Density 0.897%

    No Known Activations