© 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. 54306
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

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

    The neuron strongly activates on numeric literal tokens (i.e. numbers).

    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
    だそうです
    -0.95
     then
    -0.94
    Then
    -0.93
    그리고
    -0.91
     ಆ
    -0.90
     that
    -0.90
    줘
    -0.89
    らしいです
    -0.88
     superare
    -0.87
    낀
    -0.87
    POSITIVE LOGITS
    ➝
    1.13
     again
    1.09
    罒
    0.94
     sabemos
    0.93
     vemos
    0.91
    kém
    0.90
     dichter
    0.90
     betekent
    0.88
     aidant
    0.88
    Πηγές
    0.87
    Activations Density 0.003%

    No Known Activations