© 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. 22-GEMMASCOPE-RES-131K
    7. 28149
    Prev
    Next
    INDEX
    Explanations

    Canadian experts

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

    The neuron responds to casual, off-topic, conversational fragments—personal remarks, suggestions, and polite commentary—rather than the technical or informational parts of 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_22/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
    Kapitel
    -0.91
    トヨタ
    -0.83
    ellent
    -0.78
     hlavní
    -0.78
    乱
    -0.78
    Equipos
    -0.77
     znám
    -0.75
     Drivers
    -0.75
     Что
    -0.75
     Fifa
    -0.73
    POSITIVE LOGITS
     experts
    1.06
     professionals
    1.03
     spokesman
    0.97
     advice
    0.95
     staff
    0.94
     expert
    0.93
     website
    0.93
     expertise
    0.92
     team
    0.91
     pObj
    0.91
    Activations Density 0.145%

    No Known Activations