© 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. 12611
    Prev
    Next
    INDEX
    Explanations

    proper names ending in man/son/etc

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

    The neuron consistently fires on capitalized surname fragments of 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_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
     cristianismo
    -1.27
    ",
    -1.23
    atürk
    -1.18
     настолько
    -1.17
     ihrer
    -1.16
    嫫
    -1.15
     quando
    -1.11
    ；
    -1.10
     or
    -1.07
    蹈
    -1.07
    POSITIVE LOGITS
     his
    1.37
     that
    1.25
     njego
    1.20
     крепления
    1.17
     him
    1.17
    さてさて
    1.14
     ofere
    1.12
    已經
    1.09
     =
    1.09
    すでに
    1.09
    Activations Density 0.040%

    No Known Activations