© 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. 10-GEMMASCOPE-RES-131K
    7. 67140
    Prev
    Next
    INDEX
    Explanations

    react and angular imports

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

    This neuron detects the opening curly brace that begins a named import or destructuring block in import statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     beaucoup
    -2.20
     ì
    -1.96
     spektak
    -1.96
    蚰
    -1.85
    ﹍﹍
    -1.85
     apparaissent
    -1.83
     kulinar
    -1.83
     komfor
    -1.82
     colocando
    -1.82
     hà
    -1.80
    POSITIVE LOGITS
    </b>
    2.63
     showed
    2.22
     only
    2.20
     was
    2.13
     without
    2.06
     had
    2.06
     despite
    2.06
     may
    2.00
     two
    1.98
     took
    1.95
    Activations Density 0.003%

    No Known Activations