© 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. 48895
    Prev
    Next
    INDEX
    Explanations

    language, python, import

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

    This neuron specializes in spotting HTML or XML tag names.

    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
     then
    -1.70
     before
    -1.54
    デ
    -1.09
     перед
    -1.04
    ówczas
    -0.97
     قبل
    -0.95
     Then
    -0.94
     デ
    -0.92
    豈
    -0.91
     dann
    -0.90
    POSITIVE LOGITS
     while
    1.18
     during
    1.01
     due
    0.91
    During
    0.90
    While
    0.87
    idue
    0.87
     mentre
    0.86
     Dutta
    0.86
    Dyna
    0.86
     Duf
    0.85
    Activations Density 0.024%

    No Known Activations