© 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. 58890
    Prev
    Next
    INDEX
    Explanations

    in the context of

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

    The neuron fires on occurrences of the phrase “in the context of” (i.e. the word “context” when framing a subject).

    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
    Throttle
    -1.02
    Curl
    -0.92
     Mosca
    -0.90
     Mask
    -0.90
    Balancer
    -0.87
     vzduchu
    -0.83
    weren
    -0.82
    anzeige
    -0.81
     Türkçe
    -0.80
     tabletas
    -0.80
    POSITIVE LOGITS
     surrounding
    1.38
     context
    1.22
     provided
    1.21
    ually
    1.21
    context
    1.16
     wider
    1.11
     contextual
    1.10
     contexto
    1.09
     situate
    1.06
     broader
    1.00
    Activations Density 0.018%

    No Known Activations