© 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. 22-GEMMASCOPE-RES-131K
    7. 93305
    Prev
    Next
    INDEX
    Explanations

    new, free, available offers

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

    The neuron is detecting numeric tokens (standalone numbers and digits) 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_22/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
    volen
    -1.12
    lichte
    -1.11
    "){
    -1.05
    ärme
    -1.05
    $;
    -1.01
    听
    -1.00
    mathrm
    -1.00
    RUnlock
    -0.99
     razu
    -0.98
    ıyors
    -0.96
    POSITIVE LOGITS
     eBay
    1.16
     Please
    1.09
    чик
    1.05
    eBay
    1.04
    riert
    1.04
    themed
    1.00
     bidding
    0.98
    Please
    0.98
     bidders
    0.97
    item
    0.97
    Activations Density 0.025%

    No Known Activations