© 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. 100509
    Prev
    Next
    INDEX
    Explanations

    SQLAlchemy, db, session, models

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

    Python code related to database frameworks and object-relational mapping libraries (like SQLAlchemy, mongoengine, and similar ORMs).

    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
    ("
    -1.52
    ING
    -1.47
     pequeños
    -1.42
    :"
    -1.36
     $-
    -1.36
    絣
    -1.34
     \&
    -1.30
    ୌ
    -1.30
     $-$
    -1.30
     &#
    -1.29
    POSITIVE LOGITS
     clásica
    1.33
    ouncement
    1.22
     vond
    1.20
     altijd
    1.20
    tillery
    1.18
    を狙
    1.17
     delicada
    1.16
     cómoda
    1.15
    ソール
    1.15
    ormick
    1.15
    Activations Density 0.016%

    No Known Activations