© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74381
    Prev
    Next
    INDEX
    Explanations

    date format

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

    The neuron is looking for numeric tokens (numbers and numeric sequences, including integers and decimals).

    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
    </sup>
    -1.95
                   
    -1.77
                  
    -1.70
    葑
    -1.66
                                  
    -1.63
                     
    -1.62
     ‌
    -1.62
         
    -1.62
        
    -1.60
     ''
    -1.57
    POSITIVE LOGITS
     手順
    1.49
     beträ
    1.48
     assolutamente
    1.47
     of
    1.44
     setDescription
    1.41
    nically
    1.41
     cinturón
    1.39
    ಯ
    1.38
    グルト
    1.38
     cojín
    1.38
    Activations Density 0.089%

    No Known Activations