© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112406
    Prev
    Next
    INDEX
    Explanations

    database contexts, entities, ORMs

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

    code related to database contexts, entities, and object-relational mapping (ORM) frameworks.

    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
    tabili
    -1.21
     lur
    -1.18
     similares
    -1.10
     Fórmula
    -1.09
     Tast
    -1.09
     mulig
    -1.06
     ultimi
    -1.06
     unspeakable
    -1.05
     congratulated
    -1.05
     ava
    -1.05
    POSITIVE LOGITS
    thèse
    1.23
     from
    1.21
     encontrar
    1.20
     and
    1.20
    OnItem
    1.13
    省市镇
    1.13
    ómica
    1.09
    конец
    1.09
    şiv
    1.09
    ходит
    1.09
    Activations Density 0.050%

    No Known Activations