© 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. 22-GEMMASCOPE-RES-131K
    4. 28292
    Prev
    Next
    INDEX
    Explanations

    table/column aliases

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

    This neuron detects column references used in SQL JOIN equality conditions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    yeli
    -1.07
    kond
    -1.04
     while
    -1.04
    $.}
    -0.98
     and
    -0.95
    勿
    -0.93
    怪我
    -0.90
    贄
    -0.90
    Tapi
    -0.89
    rahat
    -0.89
    POSITIVE LOGITS
    cripts
    1.01
    各样的
    1.01
     groupBox
    1.01
    负载
    1.00
     ™
    1.00
     sugger
    1.00
    刚好
    1.00
     その他
    0.97
     अन्य
    0.97
    อื่น
    0.95
    Activations Density 0.004%

    No Known Activations