© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59869
    Prev
    Next
    INDEX
    Explanations

    personal names and brands

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

    The neuron fires on capitalized single‐word named entities (proper nouns) such as unique person, place, or organization 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_10/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
    }$
    -4.47
    c
    -3.16
    o
    -3.13
    )$
    -2.97
    f
    -2.95
    .”
    -2.86
    p
    -2.86
    Z
    -2.81
    E
    -2.77
    t
    -2.72
    POSITIVE LOGITS
    笮
    2.94
    時間も
    2.70
    鲮
    2.58
     camiset
    2.56
    
    2.52
     helicópter
    2.52
    糁
    2.39
    zapatillas
    2.34
    categorie
    2.31
     denominado
    2.31
    Activations Density 0.010%

    No Known Activations