© 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. 130937
    Prev
    Next
    INDEX
    Explanations

    people's names like Brenda, Davidson

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

    The neuron is highly activated by occurrences of the name “Brenda.”

    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
    c
    -2.91
    y
    -2.73
    или
    -2.66
    </strong>
    -2.48
     flaw
    -2.45
    他自己
    -2.42
    ......
    -2.39
    ve
    -2.39
     procedentes
    -2.31
     económicas
    -2.30
    POSITIVE LOGITS
    鴆
    2.28
    쩡
    2.25
    [
    2.25
    schuhe
    2.22
    但我
    2.20
    .
    2.17
    鯪
    2.16
    er
    2.13
    bezpiecz
    2.09
    崀
    2.08
    Activations Density 0.021%

    No Known Activations