© 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. 113678
    Prev
    Next
    INDEX
    Explanations

    SessionScoped or scoped contexts

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

    the word "scoped" in programming contexts, particularly in variable names, class names, and code identifiers.

    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
     Why
    -1.90
     But
    -1.85
     Another
    -1.78
     otras
    -1.78
     So
    -1.75
     When
    -1.74
     Their
    -1.69
     There
    -1.69
     Also
    -1.65
    一等
    -1.64
    POSITIVE LOGITS
    the
    2.22
    Scoped
    2.08
    鱨
    1.88
     jelasnya
    1.87
    <bos>
    1.86
     ujarnya
    1.85
     мы
    1.83
    they
    1.75
    3
    1.75
     markiert
    1.74
    Activations Density 0.001%

    No Known Activations