© 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. 10-GEMMASCOPE-RES-131K
    7. 19686
    Prev
    Next
    INDEX
    Explanations

    LEED, syphilis, Oprah, inbound, substantive

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

    The neuron activates on proper nouns—capitalized names of organizations, diseases, people, or groups.

    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
    “
    -2.47
     Areas
    -2.17
    多样
    -1.92
     direta
    -1.88
     handful
    -1.86
    摃
    -1.85
     coloridos
    -1.84
    lepší
    -1.83
     immense
    -1.81
    renowned
    -1.80
    POSITIVE LOGITS
    </h1>
    2.56
     specializing
    2.47
    .」
    2.20
    鶺
    2.19
    ܃
    2.19
    r
    2.17
     »)
    2.14
     производится
    2.05
     fucks
    1.99
     estrictamente
    1.98
    Activations Density 0.001%

    No Known Activations