© 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. 92559
    Prev
    Next
    INDEX
    Explanations

    pages, Member, or specific named entities

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

    The neuron specifically fires on C# code declaration keywords and identifiers—things like “using”, namespace names, “public”, “class”, and Razor Pages framework tokens.

    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
    wachung
    -0.81
    綜合
    -0.81
     wickedness
    -0.77
     Ausblick
    -0.76
    шкой
    -0.73
     Phoebe
    -0.71
    oreille
    -0.71
     vacated
    -0.69
    жалуйста
    -0.69
     dissatisfaction
    -0.68
    POSITIVE LOGITS
    สม
    0.80
    canActivate
    0.77
    strange
    0.76
     Endpoint
    0.73
    账
    0.72
    lossene
    0.71
     안
    0.71
    SizedBox
    0.70
     Appearance
    0.69
     pratic
    0.68
    Activations Density 0.031%

    No Known Activations