© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8155
    Prev
    Next
    INDEX
    Explanations

    The neuron is strongly activated by standalone numeric tokens (e.g. years, citation numbers, and other digit sequences).

    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_31_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
    ‘’
    0.73
    "...
    0.66
    �
    0.65
    ""
    0.61
    “
    0.61
    
    0.61
    “…
    0.57
     ܀
    0.56
    </u>
    0.55
    ：「
    0.54
    POSITIVE LOGITS
     《
    0.82
    ，《
    0.79
     $\%
    0.77
    -{\
    0.76
    <code>
    0.73
    《
    0.73
     `{
    0.72
     $-\
    0.72
     [$
    0.71
     #{
    0.70
    Activations Density 0.401%

    No Known Activations