© 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. 34-GEMMASCOPE-RES-131K
    7. 58441
    Prev
    Next
    INDEX
    Explanations

    release, royalty, elevated growth, mie goreng

    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
    柾
    -0.77
     Chick
    -0.77
     chip
    -0.74
     Martin
    -0.73
    Kör
    -0.72
     macroeconomic
    -0.72
     therm
    -0.72
     Track
    -0.70
     Aust
    -0.70
     Chip
    -0.70
    POSITIVE LOGITS
     royalties
    1.63
     Royalty
    1.62
     royalty
    1.54
    royal
    1.32
     Creators
    1.27
    Roy
    1.23
     creators
    1.14
     creator
    1.13
     secondary
    1.08
     listings
    1.08
    Activations Density 0.002%

    No Known Activations