© 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. 60448
    Prev
    Next
    INDEX
    Explanations

    names, family members, professions

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

    The neuron strongly responds to capitalized proper‐noun tokens—especially personal names.

    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
    Wayne
    -0.99
    codings
    -0.91
    Singh
    -0.90
     Darlene
    -0.89
    canActivate
    -0.89
    dengan
    -0.87
     Sampson
    -0.86
    ränke
    -0.85
    Diamond
    -0.85
    Rachel
    -0.85
    POSITIVE LOGITS
     Episcopal
    1.29
    Epis
    1.19
     architecture
    1.05
    Mimi
    0.91
     cocktail
    0.89
     skiing
    0.88
    Margot
    0.86
     Auch
    0.82
     lawyer
    0.81
     Sitten
    0.80
    Activations Density 0.100%

    No Known Activations