© 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. 127305
    Prev
    Next
    INDEX
    Explanations

    names Stefan and Stefano

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

    The neuron selectively activates on occurrences of the proper name “Stefan.”

    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
     Could
    -3.16
     You
    -3.11
     prenotazione
    -2.67
     Indeed
    -2.58
     Technically
    -2.52
     The
    -2.41
     Exactly
    -2.39
     dicono
    -2.39
     tormented
    -2.39
    $>$
    -2.38
    POSITIVE LOGITS
    鏟
    2.31
     可爱
    2.30
    W
    2.27
     輕
    2.25
     dont
    2.23
    鹀
    2.20
    up
    2.20
     deres
    2.14
     兒童
    2.14
    运作
    2.13
    Activations Density 0.004%

    No Known Activations