© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104748
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and calculations

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

    This neuron fires on numeric superscript tokens (e.g. the “^{...}” parts) in LaTeX-style math expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -4.59
    For
    -3.59
    (
    -3.48
    9
    -3.48
    When
    -3.03
    6
    -3.02
    5
    -3.02
     For
    -3.00
        
    -2.97
     –
    -2.95
    POSITIVE LOGITS
    }^{
    3.55
    
    3.08
    珵
    2.98
    狳
    2.94
    瘣
    2.91
    沵
    2.91
    횃
    2.81
    鼋
    2.77
     帅气
    2.75
    奁
    2.73
    Activations Density 0.002%

    No Known Activations