© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and results

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting numerical and quantitative details—numbers (often with units or decimals) that describe measurements, quantities, or amounts.

    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
     kaa
    0.68
    
    0.61
    思考
    0.58
     kalian
    0.57
     przedstaw
    0.56
     uncertainties
    0.55
     tahu
    0.55
    hann
    0.55
    的关系
    0.54
    apro
    0.54
    POSITIVE LOGITS
     क्लिक
    0.64
     Round
    0.63
     ROUND
    0.59
    従
    0.59
     Formatting
    0.58
     Doctorate
    0.58
     Click
    0.57
    Click
    0.56
     তৈরী
    0.56
    良く
    0.55
    Activations Density 0.023%

    No Known Activations