© 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. 80026
    Prev
    Next
    INDEX
    Explanations

    like a

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

    The neuron fires on numeric tokens (numbers and numerical figures) 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
     then
    -1.25
    Р
    -1.08
     about
    -1.08
    属于
    -0.99
    屬於
    -0.98
    ременно
    -0.96
    
    -0.96
     Evaluating
    -0.95
    感动
    -0.95
     exemplified
    -0.95
    POSITIVE LOGITS
    🫴
    1.14
    vinner
    1.13
     завжди
    1.11
    chaussures
    1.09
    ushman
    1.05
     збіль
    1.05
     other
    1.04
     Tämä
    1.03
    虔
    1.03
     никогда
    1.02
    Activations Density 0.016%

    No Known Activations