© 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. 450
    Prev
    Next
    INDEX
    Explanations

    sorting by asc and desc

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

    The neuron fires on SQL sort‐order keywords (“ASC” or “DESC”) in ORDER BY clauses.

    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
    CUIT
    -1.23
     oa
    -1.06
     of
    -1.05
     volna
    -1.01
    ВД
    -0.98
     a
    -0.97
    QUÉ
    -0.96
    SID
    -0.95
     início
    -0.94
    -
    -0.94
    POSITIVE LOGITS
    戕
    1.23
    Коммента
    1.22
    Those
    1.17
    You
    1.12
    If
    1.09
    Many
    1.08
    Pá
    1.06
    Цели
    1.06
    There
    1.05
    Another
    1.05
    Activations Density 0.002%

    No Known Activations