© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119490
    Prev
    Next
    INDEX
    Explanations

    contribute to

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

    The neuron strongly activates on numeric expressions (e.g. digits, decimals, percentages)—in other words it flags tokens that are part of numbers or numeric data.

    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
    不宜
    -1.47
     names
    -1.44
     avec
    -1.41
     for
    -1.41
     tomando
    -1.35
     ciudadana
    -1.35
    apatalk
    -1.34
    惴
    -1.33
     Literary
    -1.33
     inget
    -1.32
    POSITIVE LOGITS
    brtc
    1.75
     spagno
    1.73
    uegos
    1.73
    banez
    1.66
     nonché
    1.65
    lorin
    1.63
     ...
    
    1.48
    dotto
    1.48
    onné
    1.48
    Según
    1.45
    Activations Density 0.023%

    No Known Activations