© 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. 198
    Prev
    Next
    INDEX
    Explanations

    github.com/questions/java

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

    This neuron detects function or method‐call tokens—especially the opening parenthesis and accompanying line‐number indicators common in programming stack traces.

    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
    [])
    -1.20
    =="
    -1.19
     Ausdrücke
    -1.02
     contextLoads
    -1.01
    nees
    -1.00
    ++.
    -0.99
    "--
    -0.99
    aneity
    -0.98
     imagina
    -0.97
     estrada
    -0.97
    POSITIVE LOGITS
     好看
    1.12
     geschlagen
    1.09
     vœ
    1.07
     или
    1.05
    Boxscore
    1.05
    Postup
    1.05
    Ered
    1.05
     verkligen
    1.02
    diğ
    1.00
    Svet
    0.99
    Activations Density 0.002%

    No Known Activations