© 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. 3589
    Prev
    Next
    INDEX
    Explanations

    being, after, during, help, in addition

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

    The neuron is chiefly triggered by numeric tokens—integers, decimals, and other digit-based values—in the text.

    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
    
    -1.64
    <bos>
    -1.48
     such
    -1.48
     anything
    -1.44
     xvii
    -1.43
     whatever
    -1.43
     yako
    -1.42
     yng
    -1.40
     not
    -1.39
     habari
    -1.38
    POSITIVE LOGITS
     during
    2.22
     after
    2.11
     pretože
    2.06
    щены
    1.97
    hướng
    1.87
     protože
    1.80
    đại
    1.80
     help
    1.76
    dịch
    1.76
    nhà
    1.73
    Activations Density 0.067%

    No Known Activations