© 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. 34-GEMMASCOPE-RES-131K
    7. 115655
    Prev
    Next
    INDEX
    Explanations

    database sql queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Crowd
    -0.81
    ㄨ
    -0.73
    udara
    -0.73
    engager
    -0.73
     nirvana
    -0.72
    ǽ
    -0.71
     mese
    -0.71
     Econom
    -0.70
    üman
    -0.69
    )$\\
    -0.68
    POSITIVE LOGITS
    sql
    2.44
     sql
    2.41
     SQL
    2.16
     query
    1.90
    SQL
    1.76
    query
    1.64
     queries
    1.52
    Sql
    1.48
    语句
    1.45
    CommandText
    1.45
    Activations Density 0.051%

    No Known Activations