© 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. 48731
    Prev
    Next
    INDEX
    Explanations

    Visio diagrams

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

    The neuron fires on references to diagram‐oriented tooling and file paths—especially mentions of MS Visio, UML/sequence diagrams, and their related menu or XML shape definitions.

    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
    Ḏ
    -0.85
    pulver
    -0.81
    localisation
    -0.79
    ACP
    -0.77
     写真
    -0.77
    glUniform
    -0.76
    село
    -0.74
    ロボット
    -0.73
    muffin
    -0.72
    侠
    -0.72
    POSITIVE LOGITS
     diagram
    2.59
     diagrams
    2.48
    diagram
    2.06
     Diagram
    2.02
     diag
    1.98
    Diagram
    1.96
     Diagrams
    1.88
     DIAGRAM
    1.76
     drawing
    1.76
     UML
    1.73
    Activations Density 0.113%

    No Known Activations