© 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. 104970
    Prev
    Next
    INDEX
    Explanations

    matching and interfacing

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

    the word "matching" in technical contexts, particularly in patent and scientific documents describing alignment, compatibility, or correspondence between components or signals.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on technical nominalizations—words naming processes or operations (e.g. “matching,” “interfacing,” “factorisation,” etc.).

    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
     formación
    -1.34
    着脸
    -1.30
     onderdelen
    -1.27
     mógł
    -1.27
    ="'+
    -1.22
    ників
    -1.22
     antigüedad
    -1.21
     ingeniería
    -1.18
     comprensión
    -1.18
     cerámica
    -1.18
    POSITIVE LOGITS
     the
    1.88
     другими
    1.39
     между
    1.28
     between
    1.26
     I
    1.21
    up
    1.20
     другие
    1.15
    ряду
    1.11
     است
    1.11
    ท์
    1.09
    Activations Density 0.117%

    No Known Activations