© 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. 420
    Prev
    Next
    INDEX
    Explanations

    .NET System namespace code

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

    The neuron detects occurrences of the “System” token in fully qualified .NET type 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
    Ğ
    -0.88
    โคร
    -0.87
    ﾚ
    -0.87
     at
    -0.84
    corbic
    -0.82
    カリ
    -0.79
     Holders
    -0.75
     with
    -0.75
    復帰
    -0.74
    教材
    -0.73
    POSITIVE LOGITS
     bestimmen
    0.89
     tarjo
    0.88
     ($('#
    0.88
    ową
    0.88
     universitaria
    0.88
     たい
    0.85
    ʊ
    0.85
    óticas
    0.84
    𐌿
    0.84
    裳
    0.82
    Activations Density 0.003%

    No Known Activations