© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72833
    Prev
    Next
    INDEX
    Explanations

    escape sequences and special characters

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

    The neuron fires on numeric literals (digits) in code snippets.

    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
    signable
    -1.05
    ？？
    -1.05
     in
    -1.00
     atmosfera
    -0.99
    。。。。
    -0.98
    ？！
    -0.97
     vaksin
    -0.96
     otot
    -0.95
    ண்ட
    -0.94
     sekunder
    -0.94
    POSITIVE LOGITS
     nötig
    1.05
     beispielsweise
    0.98
     gewohnt
    0.96
     volvió
    0.95
     Цена
    0.94
     anfangs
    0.94
     zweimal
    0.93
     چگونه
    0.91
     Каждый
    0.91
     geplant
    0.91
    Activations Density 0.007%

    No Known Activations