© 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. 34-GEMMASCOPE-RES-131K
    7. 49620
    Prev
    Next
    INDEX
    Explanations

    introducing a topic or question

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

    This neuron detects Mapster’s fluent‐API mapping calls in C# code, i.e. method-chain expressions like “Map(… => …).IgnoreNonMapped(…)” involving the lambda arrow operator.

    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
     appended
    -0.86
    Ҳ
    -0.83
     WSU
    -0.82
     アメリカ
    -0.82
     fometimes
    -0.81
    Учитель
    -0.79
    Étymologie
    -0.78
    螻
    -0.77
    AddArg
    -0.77
     Большая
    -0.76
    POSITIVE LOGITS
    HasColumnName
    0.95
    ↵↵↵
    0.82
    ņem
    0.78
    tablename
    0.76
     Price
    0.76
    ↵↵↵↵
    0.75
    nk
    0.75
    octet
    0.74
     Serv
    0.74
    san
    0.73
    Activations Density 0.006%

    No Known Activations