© 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. 60504
    Prev
    Next
    INDEX
    Explanations

    time to do things

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

    The neuron activates on decimal numeric tokens (floating‐point numbers, often in ranges).

    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
     
    -2.20
    </sup>
    -1.98
     by
    -1.81
    妺
    -1.80
     no
    -1.77
     most
    -1.74
     papild
    -1.74
     to
    -1.73
     “
    -1.73
     ‘
    -1.68
    POSITIVE LOGITS
     イラストレーション
    1.74
    ⵣ
    1.73
    ㍑
    1.72
    
    1.72
     火鍋
    1.67
    龊
    1.66
     accla
    1.64
     كيف
    1.63
     Superhosts
    1.62
    らせて
    1.61
    Activations Density 0.014%

    No Known Activations