© 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. 110850
    Prev
    Next
    INDEX
    Explanations

    ASP.NET

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

    The neuron is looking for programming‐code tokens—particularly common syntax and keywords (e.g. “using”, “.NET”, “part”, “of”, punctuation like “.”) that signal code or namespace references.

    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
    vės
    -0.79
    ترا
    -0.76
    生效
    -0.70
     hustle
    -0.70
     信
    -0.69
     стабили
    -0.69
     renforcé
    -0.68
     Bruch
    -0.67
     Erie
    -0.67
    tuin
    -0.67
    POSITIVE LOGITS
     NET
    3.20
    NET
    3.19
     net
    2.30
    net
    2.27
    Net
    2.23
     Net
    2.23
    dotnet
    2.17
    DotNet
    2.02
     dot
    1.49
     nett
    1.45
    Activations Density 0.285%

    No Known Activations