© 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. 39142
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

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

    This neuron primarily responds to proper nouns, especially personal names.

    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
    睺
    -2.64
    
    -2.48
     mede
    -2.47
     helle
    -2.36
     スペシャル
    -2.33
    但也
    -2.33
     fai
    -2.33
     позволит
    -2.31
     getNombre
    -2.25
     uly
    -2.25
    POSITIVE LOGITS
    )
    2.45
     This
    2.42
    していた
    2.39
     Why
    2.31
     There
    2.25
    cault
    2.25
     條
    2.23
     เป็น
    2.22
     You
    2.20
    jenigen
    2.16
    Activations Density 0.481%

    No Known Activations