© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72560
    Prev
    Next
    INDEX
    Explanations

    identifiers like class, id, controller

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

    This neuron flags C# anonymous‐object initializers (the “new { … }” syntax).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ers
    -1.37
    把它
    -1.33
     first
    -1.27
    犼
    -1.21
    RootElement
    -1.21
    现在的
    -1.21
     in
    -1.21
    -1.20
    section
    -1.19
    ”,
    -1.19
    POSITIVE LOGITS
    características
    1.38
     tomates
    1.34
     Venise
    1.33
     África
    1.31
    mejores
    1.30
     detalló
    1.29
     agregó
    1.28
    棐
    1.27
    ة
    1.27
     但
    1.26
    Activations Density 0.004%

    No Known Activations