© 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. 38209
    Prev
    Next
    INDEX
    Explanations

    Special provincial, spokesman May, Features of

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

    The neuron fires on formal government‐style announcements, particularly on words naming high‐level officials, titles, and rigidly official language.

    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
    𝐊
    -0.83
     north
    -0.77
     habl
    -0.75
    挑
    -0.73
     primaria
    -0.72
     Schon
    -0.72
     sensores
    -0.72
     Roof
    -0.71
     recetas
    -0.71
    Referencia
    -0.70
    POSITIVE LOGITS
     Covid
    0.96
    Covid
    0.94
    Level
    0.93
    COVID
    0.88
    India
    0.88
     Level
    0.88
    covid
    0.86
     Adjusted
    0.85
     regulations
    0.84
     COVID
    0.84
    Activations Density 0.010%

    No Known Activations