© 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. 22-GEMMASCOPE-RES-131K
    7. 71783
    Prev
    Next
    INDEX
    Explanations

    setting variables in code

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

    This neuron primarily activates on the opening‐parenthesis character “(,” especially in code or function/macro call contexts.

    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
     viele
    -1.16
    Zubereitung
    -1.15
     then
    -1.07
    ContentAlignment
    -1.07
    ParallelGroup
    -1.02
    edin
    -1.02
    RectangleBorder
    -1.02
    ]")]
    -1.02
    (!__
    -1.02
    麃
    -1.02
    POSITIVE LOGITS
     you
    1.43
     tornillos
    1.17
     egentligen
    1.16
    溅
    1.13
     säkert
    1.10
     وَ
    1.10
     your
    1.09
    かったので
    1.07
     antiguas
    1.05
     gjerne
    1.03
    Activations Density 0.001%

    No Known Activations