© 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. 130615
    Prev
    Next
    INDEX
    Explanations

    This neuron responds strongly to code‐style parentheses tokens (in particular the “()” that denote function calls or definitions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    finalizing outputs or references

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    (;;)
    -1.07
     (;;)
    -1.06
                            
    -0.98
    ใน
    -0.97
                         
    -0.95
     tropicales
    -0.93
                           
    -0.92
    FORD
    -0.90
    </sup>
    -0.90
    एं
    -0.90
    POSITIVE LOGITS
     final
    1.23
     success
    1.21
     concluding
    1.19
     outro
    1.14
    Final
    1.14
     overall
    1.13
     finished
    1.13
    velles
    1.13
     النها
    1.07
     Nachhal
    1.05
    Activations Density 0.001%

    No Known Activations