© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78685
    Prev
    Next
    INDEX
    Explanations

    words starting with Ye or Yes

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

    The neuron fires on tokens beginning with the letter sequence “Ye,” i.e. words or names that start with “Ye.”

    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
    不住
    -0.84
    abadi
    -0.78
    tillas
    -0.75
     inversiones
    -0.75
    ссажи
    -0.75
    neming
    -0.74
    Descubre
    -0.73
    が多い
    -0.72
    もしか
    -0.72
    蒨
    -0.71
    POSITIVE LOGITS
    姉妹
    0.90
    olde
    0.85
    щ
    0.82
    YesNo
    0.79
     Ye
    0.79
    Defined
    0.78
    engue
    0.76
    Capacity
    0.76
    terday
    0.75
    India
    0.75
    Activations Density 0.013%

    No Known Activations