© 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. 42125
    Prev
    Next
    INDEX
    Explanations

    surrogate

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

    The neuron activates on the token “surrogate” (and its compounds, e.g. “surrogate keys,” “surrogate mothers,” “surrogate markers”).

    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
    訁
    -2.31
    氿
    -2.23
    
    -2.14
    咵
    -2.11
    荭
    -2.11
    ៚
    -2.09
    菝
    -2.08
    擽
    -2.08
    derdag
    -2.05
     история
    -2.03
    POSITIVE LOGITS
    刧
    2.28
    to
    2.20
     撮っ
    2.13
    accéder
    1.98
     surrogate
    1.91
     Surrogate
    1.84
    九月
    1.84
    了什么
    1.82
    OUTUBE
    1.80
    ïlande
    1.79
    Activations Density 0.005%

    No Known Activations