© 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. 102108
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

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

    This neuron responds to programming identifiers—especially multiword or Pascal/Camel-cased names like class names, method calls, component names, and other API symbols.

    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
     adecuados
    -1.38
    SPAR
    -1.34
    のも
    -1.28
     nét
    -1.28
    ONLY
    -1.27
     ܐ
    -1.27
    わせて
    -1.27
     tumultuous
    -1.26
    着一个
    -1.23
     deux
    -1.19
    POSITIVE LOGITS
     in
    1.61
     furthering
    1.54
     began
    1.45
     went
    1.38
     with
    1.31
     dwindling
    1.26
     noticeable
    1.24
     start
    1.24
     conector
    1.23
     during
    1.20
    Activations Density 0.033%

    No Known Activations