© 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. 10-GEMMASCOPE-RES-131K
    7. 43890
    Prev
    Next
    INDEX
    Explanations

    Eclipse Java programming

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

    The neuron fires on mentions of Eclipse/SWT (and related Java UI) toolkit classes and APIs.

    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
     gewi
    -1.68
     ſta
    -1.65
     casio
    -1.57
     ferrari
    -1.52
     ensu
    -1.51
     sprüche
    -1.50
     doman
    -1.48
     Gladiator
    -1.47
     niedersachsen
    -1.45
     kaiser
    -1.45
    POSITIVE LOGITS
     ON
    1.66
     nicht
    1.54
     développé
    1.52
     Does
    1.48
     In
    1.46
     With
    1.46
     Not
    1.44
     I
    1.44
     jeho
    1.41
    swt
    1.41
    Activations Density 0.009%

    No Known Activations