© 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. 99610
    Prev
    Next
    INDEX
    Explanations

    GWT and RPC

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

    The neuron is tuned to spot occurrences of the acronym “GWT” (and closely related technical “GWT”‐based terms) in the document.

    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
    ɟ
    -0.79
     cluster
    -0.75
     GLFW
    -0.75
    bida
    -0.73
    🦯
    -0.72
    macos
    -0.71
    grams
    -0.71
    sscanf
    -0.70
    ToMap
    -0.70
    gla
    -0.69
    POSITIVE LOGITS
     RPC
    1.02
    Permutation
    0.87
    Indianapolis
    0.86
    Visualization
    0.84
     Evansville
    0.83
    衛生
    0.78
     serialization
    0.78
    mvp
    0.78
    rpc
    0.75
    Reveal
    0.75
    Activations Density 0.010%

    No Known Activations