© 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. 34-GEMMASCOPE-RES-131K
    7. 57310
    Prev
    Next
    INDEX
    Explanations

    C#/.NET code snippets

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

    The neuron strongly fires on numeric literals (tokens composed of digits) in code.

    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
    ذلك
    -0.84
     stratigraphy
    -0.81
    osen
    -0.80
     {
    -0.79
    Ꮷ
    -0.77
     JTextField
    -0.76
    Stdout
    -0.76
    窒
    -0.76
    愍
    -0.75
    toastr
    -0.75
    POSITIVE LOGITS
    foreach
    1.00
     await
    0.86
    ISupport
    0.83
    var
    0.81
    [,]
    0.77
    #
    0.77
    migrationBuilder
    0.73
     aside
    0.73
    sigmoid
    0.71
    既然
    0.71
    Activations Density 0.012%

    No Known Activations