© 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. 81590
    Prev
    Next
    INDEX
    Explanations

    professional clothing and accessories

    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
     hoodies
    -0.93
     hoodie
    -0.92
     snorted
    -0.85
     bearded
    -0.84
     denim
    -0.82
    Fragment
    -0.82
    лимпий
    -0.81
    ॉग
    -0.81
    beard
    -0.80
     Fragment
    -0.79
    POSITIVE LOGITS
     blazer
    1.17
     professional
    0.96
     tailored
    0.94
     office
    0.94
     business
    0.94
     ponte
    0.90
     structured
    0.88
     pumps
    0.88
     Professional
    0.88
     Blazer
    0.85
    Activations Density 0.021%

    No Known Activations