© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90781
    Prev
    Next
    INDEX
    Explanations

    code syntax and structures

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

    This neuron fires on programming keywords that introduce control-flow or block constructs (e.g. switch, catch, function).

    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
     connaissent
    -0.90
     esteja
    -0.88
     investir
    -0.86
     pará
    -0.85
     enfans
    -0.84
    Incluye
    -0.84
    に対
    -0.82
     pê
    -0.82
     amazingly
    -0.81
     chirurgie
    -0.81
    POSITIVE LOGITS
     ,
    1.24
     ).
    0.97
     ),
    0.96
     University
    0.92
     );
    0.91
     '))
    0.86
     )
    0.84
     Resource
    0.84
     or
    0.81
     ,
    
    0.77
    Activations Density 0.003%

    No Known Activations