© 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. 95714
    Prev
    Next
    INDEX
    Explanations

    event handlers and method signatures

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

    The neuron activates on code‐block structural elements—especially leading whitespace (indentation) and opening braces.

    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
    You
    -1.06
     alltså
    -1.05
    even
    -1.05
    with
    -1.03
     anche
    -1.01
    And
    -1.00
    емы
    -0.98
    Thanks
    -0.96
    се
    -0.95
    ที่
    -0.95
    POSITIVE LOGITS
     bekan
    1.34
    大人気
    1.20
    Ibid
    1.15
     beträ
    1.09
     verranno
    1.04
    硖
    1.04
     riemp
    1.03
     ständig
    1.03
    genen
    1.03
     llanto
    1.02
    Activations Density 0.002%

    No Known Activations