© 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. 34-GEMMASCOPE-RES-131K
    7. 33473
    Prev
    Next
    INDEX
    Explanations

    customer quality relationships

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

    This neuron detects passages listing a company’s core values or principles (e.g. enumerations of “openness, transparency, fairness, innovation, empowerment,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    chè
    -1.10
    HostException
    -1.09
    ambassade
    -1.01
     ***!
    -0.96
    bodied
    -0.96
    нева
    -0.95
    udahkan
    -0.94
     språk
    -0.93
    тивы
    -0.93
    hogs
    -0.92
    POSITIVE LOGITS
     customer
    2.67
     quality
    2.20
    customer
    1.78
     client
    1.77
     Customer
    1.67
     integrity
    1.66
    Customer
    1.65
     innovation
    1.64
     honesty
    1.61
     relationships
    1.58
    Activations Density 0.050%

    No Known Activations