© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45660
    Prev
    Next
    INDEX
    Explanations

    Light followed by compound words

    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
    Comun
    -0.91
    ed
    -0.84
     restless
    -0.83
     MSI
    -0.80
    td
    -0.79
     Announced
    -0.79
     vents
    -0.78
    ↵
    -0.76
     loud
    -0.75
     Demonstrate
    -0.75
    POSITIVE LOGITS
    bulb
    1.94
    hearted
    1.72
    ened
    1.56
    NING
    1.52
     Light
    1.43
    light
    1.38
    nings
    1.36
     hearted
    1.36
     LIGHT
    1.33
     light
    1.31
    Activations Density 0.035%

    No Known Activations