© 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. 72892
    Prev
    Next
    INDEX
    Explanations

    Andrei Markov, Gabor, Luxley

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

    The neuron is primarily activated by occurrences of the proper name “Andrei.”

    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
     negotiator
    -2.34
    ന്‍
    -2.20
    !
    -2.17
     slew
    -2.13
    jewództ
    -2.13
    其妙
    -2.11
    ),
    -2.11
     spectre
    -2.09
    AdvEx
    -2.06
    )$
    -1.99
    POSITIVE LOGITS
    ing
    2.83
    a
    2.61
    慙
    2.58
    </h2>
    2.55
     diminta
    2.47
     baumwolle
    2.34
    Of
    2.34
     sempat
    2.31
    CONCLUSIONES
    2.31
    harapkan
    2.28
    Activations Density 0.013%

    No Known Activations