© 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. 102230
    Prev
    Next
    INDEX
    Explanations

    words starting with "Reg"

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

    The neuron strongly activates on the three‐letter sequence “Reg,” i.e. tokens beginning with the exact prefix Reg.

    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
    悫
    -2.88
    ',
    -2.88
    
    -2.72
    荦
    -2.64
     of
    -2.58
    潆
    -2.50
    .\\
    -2.45
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -2.45
     Produkten
    -2.42
    忖
    -2.42
    POSITIVE LOGITS
    There
    3.75
    The
    3.42
    Because
    3.28
    In
    3.28
    Since
    3.28
    d
    3.19
    ’
    3.06
    Perhaps
    3.03
    Even
    2.92
    Although
    2.92
    Activations Density 0.002%

    No Known Activations