© 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. 34-GEMMASCOPE-RES-131K
    4. 6974
    Prev
    Next
    INDEX
    Explanations

    Yi followed by names or technical terms

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

    The neuron consistently fires on the character sequence “yi” (and its variants) appearing in names or identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    愈
    -0.82
     than
    -0.81
    functional
    -0.77
     posses
    -0.75
     Tatsache
    -0.75
    aggregate
    -0.74
     más
    -0.74
    춤
    -0.72
    Functional
    -0.68
    Martin
    -0.67
    POSITIVE LOGITS
     葉
    0.85
     lukisan
    0.83
    ватися
    0.82
     alimente
    0.81
     estran
    0.80
    濞
    0.79
    蔺
    0.77
    ,:);
    0.77
     GIO
    0.76
     завжди
    0.76
    Activations Density 0.009%

    No Known Activations