© 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. 65607
    Prev
    Next
    INDEX
    Explanations

    render and return statements

    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
     najdete
    -0.84
    леп
    -0.82
     bewegen
    -0.80
     trabalhando
    -0.79
    ⁑
    -0.79
    buen
    -0.79
     appartenant
    -0.78
     ediciones
    -0.78
    กระท
    -0.77
    gehende
    -0.77
    POSITIVE LOGITS
     render
    1.59
     JS
    1.55
    jsx
    1.48
     content
    1.45
    JS
    1.41
     rendered
    1.34
    render
    1.30
     children
    1.28
     components
    1.26
     rendering
    1.22
    Activations Density 0.012%

    No Known Activations