© 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. 34-GEMMASCOPE-RES-131K
    7. 76354
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    The neuron is strongly activated by personal names (capitalized names of people).

    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
    动力
    -0.76
    zept
    -0.75
     loud
    -0.75
     میک
    -0.74
    Bele
    -0.73
     whenever
    -0.72
    buckle
    -0.72
     multiplicative
    -0.72
    Whenever
    -0.71
     кіль
    -0.70
    POSITIVE LOGITS
     '"'
    0.81
     család
    0.79
     acara
    0.78
     jars
    0.75
    TERMS
    0.75
     zuen
    0.74
    Gadget
    0.74
    thanx
    0.73
    ドキ
    0.73
     degenerative
    0.73
    Activations Density 0.043%

    No Known Activations