© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    Dumb Starbucks, Field of Invention, Registration Process

    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
    Cpu
    -0.79
    cpu
    -0.78
    shein
    -0.70
     маль
    -0.69
    CPU
    -0.67
    yeezy
    -0.66
    silly
    -0.66
     reacción
    -0.66
     любые
    -0.66
    bouncy
    -0.66
    POSITIVE LOGITS
    psum
    0.95
    tile
    0.94
     systolic
    0.82
    CascadeType
    0.81
     moza
    0.81
    ߴ
    0.80
    ̔
    0.79
     tile
    0.79
     работников
    0.79
     Address
    0.77
    Activations Density 0.004%

    No Known Activations