© 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. 79717
    Prev
    Next
    INDEX
    Explanations

    Prophylaxis or Welcome

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

    The neuron responds to instances of empty parentheses (i.e. “()”) in code, marking function declarations or calls with no arguments.

    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
     without
    -1.52
     by
    -1.28
     Without
    -1.26
     provide
    -1.25
     Creating
    -1.22
     epitom
    -1.22
     despite
    -1.19
     cleverly
    -1.17
     before
    -1.14
     like
    -1.13
    POSITIVE LOGITS
     insanely
    1.28
     myriad
    1.26
     Dinas
    1.21
     majestic
    1.19
     boister
    1.17
    atized
    1.16
     sám
    1.16
     marvelous
    1.15
     astonishing
    1.14
     wondrous
    1.14
    Activations Density 0.000%

    No Known Activations