© 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. 34-GEMMASCOPE-RES-131K
    7. 66204
    Prev
    Next
    INDEX
    Explanations

    c# programming constructs

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

    The neuron fires on numeric literal tokens (integer constants) in the code.

    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
     information
    -0.86
    zī
    -0.84
    เหมือน
    -0.78
     hukuman
    -0.77
     takk
    -0.77
     anyone
    -0.75
    ziek
    -0.75
     acondicionado
    -0.75
     analysis
    -0.74
     taas
    -0.74
    POSITIVE LOGITS
    var
    1.36
     var
    1.04
    ash
    0.93
     PSR
    0.85
     Console
    0.84
    somewhere
    0.84
     bool
    0.83
     nub
    0.83
     const
    0.82
    cshtml
    0.81
    Activations Density 0.018%

    No Known Activations