© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12117
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially floating-point numbers or decimal values.

    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
    Cursors
    0.58
    ♀
    0.58
    흥
    0.58
    adple
    0.57
     여자
    0.57
    
    0.55
    女性
    0.54
    女子
    0.54
     жі
    0.53
     femelles
    0.52
    POSITIVE LOGITS
     $$
    1.05
     $$\
    0.90
    $$
    0.89
    ,$$
    0.87
    <blockquote>
    0.77
    ```
    0.76
     ```
    0.73
    $$\
    0.69
    .$$
    0.66
    <code>
    0.63
    Activations Density 0.017%

    No Known Activations