© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77616
    Prev
    Next
    INDEX
    Explanations

    code structure definition

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

    This neuron fires on programming‐language statement starters and reserved keywords (e.g. import, const, class, require, describe) that flag the beginnings of code 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_34/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
    textura
    -1.24
    Leírás
    -1.23
     umur
    -1.22
     cuma
    -1.20
     phénom
    -1.20
     jeruk
    -1.17
     ekst
    -1.15
    nhung
    -1.14
    Eventos
    -1.14
     เปิด
    -1.12
    POSITIVE LOGITS
     game
    1.77
     item
    1.55
     movie
    1.45
     payment
    1.45
     menu
    1.43
     login
    1.42
     music
    1.41
     quiz
    1.40
     games
    1.39
     Game
    1.39
    Activations Density 0.179%

    No Known Activations