© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130992
    Prev
    Next
    INDEX
    Explanations

    cdkDrag directive and material components

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

    This neuron detects mentions of Angular’s component libraries—especially the “CDK” drag-and-drop module and Material (“mat,” “material”) components.

    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
     from
    -1.65
     after
    -1.55
     while
    -1.45
     pemikiran
    -1.45
     which
    -1.40
     uniquely
    -1.39
     (‘
    -1.38
    难怪
    -1.38
    他の
    -1.36
    pesan
    -1.35
    POSITIVE LOGITS
    fusions
    1.48
    ferences
    1.46
    ätigung
    1.45
    czywiście
    1.41
    Karena
    1.41
    ↵↵
    1.41
    cisive
    1.38
    Amicalement
    1.38
    cised
    1.37
    vaders
    1.37
    Activations Density 0.001%

    No Known Activations