© 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. 10-GEMMASCOPE-RES-131K
    7. 103436
    Prev
    Next
    INDEX
    Explanations

    new item or feature

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

    The neuron fires on capitalized software names, UI labels, and technical menu or template terms (e.g. Visual Studio, ASP .NET, Property Manager, XML).

    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
     یکی
    -1.52
    ţin
    -1.49
    Institut
    -1.48
    rajz
    -1.45
     jednej
    -1.42
    ۹
    -1.41
     déclar
    -1.41
     السياسي
    -1.41
     allemand
    -1.38
     drzwi
    -1.38
    POSITIVE LOGITS
     for
    2.63
     in
    2.50
     from
    2.05
     by
    1.99
     not
    1.84
     or
    1.81
     this
    1.69
     if
    1.69
     out
    1.69
     about
    1.65
    Activations Density 0.105%

    No Known Activations