© 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. 34740
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
    NameExpr
    -0.80
    egd
    -0.74
    ƴ
    -0.72
    。】
    -0.72
    叶凌天
    -0.72
    zell
    -0.71
     logement
    -0.71
    狹
    -0.71
    name
    -0.70
     Zorn
    -0.70
    POSITIVE LOGITS
     class
    1.65
     classes
    1.52
     method
    1.30
     field
    1.22
    class
    1.14
     Classes
    1.10
     fields
    1.08
     Class
    1.03
    classes
    1.03
     function
    1.02
    Activations Density 0.067%

    No Known Activations