© 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. 12634
    Prev
    Next
    INDEX
    Explanations

    showroom and GFR

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

    The neuron fires on mentions of “showroom” (including related phrases like “showroom floor” or “ex-showroom”).

    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
    >
    -2.77
    1
    -2.63
     \
    -2.55
    ↵
    -2.48
    
    -2.34
     That
    -2.28
     или
    -2.20
    籥
    -2.17
     که
    -2.13
    或許
    -2.08
    POSITIVE LOGITS
    。“
    2.59
    飧
    2.58
    翕
    2.36
    _
    2.22
     actie
    2.11
    沨
    2.08
     baden
    2.02
     appearance
    2.02
     disseminating
    2.02
     soo
    2.00
    Activations Density 0.001%

    No Known Activations