© 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. 19364
    Prev
    Next
    INDEX
    Explanations

    NetBeans, VisualStudio, IDEs

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

    The neuron detects mentions of the “NetBeans” IDE (and similar proper software names) in the text.

    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
    謌
    -2.50
    蚍
    -2.31
    𓇼
    -2.30
    釙
    -2.14
    愎
    -2.06
    溷
    -1.99
    哐
    -1.98
    珧
    -1.97
    琁
    -1.95
     plafon
    -1.94
    POSITIVE LOGITS
     dergleichen
    2.47
    ."
    2.44
    )
    2.38
     need
    2.22
    .
    2.20
    忻
    2.20
     ندارد
    2.17
     You
    2.14
    netbeans
    2.11
     ältere
    2.08
    Activations Density 0.002%

    No Known Activations