© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100015
    Prev
    Next
    INDEX
    Explanations

    SQL variable declarations

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

    variable declarations or assignments in SQL code, particularly those using the `@` symbol for variable names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     of
    -1.65
    轨道
    -1.45
     antworte
    -1.40
    棪
    -1.38
     Making
    -1.35
    缜
    -1.35
    ၜ
    -1.34
    льзя
    -1.34
    ílica
    -1.34
     departement
    -1.33
    POSITIVE LOGITS
     unn
    1.71
    ladı
    1.57
     necesitar
    1.48
    
    1.46
     relativement
    1.46
     telah
    1.46
    ⎔
    1.42
    mathrm
    1.41
     famed
    1.40
     esche
    1.40
    Activations Density 0.000%

    No Known Activations