© 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. 30900
    Prev
    Next
    INDEX
    Explanations

    partnerships

    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
     mixed
    -0.84
     solo
    -0.74
     сме
    -0.71
    حدى
    -0.70
    ühen
    -0.69
    getDevice
    -0.69
    の大
    -0.68
     Hearing
    -0.67
     sesi
    -0.67
    mixed
    -0.66
    POSITIVE LOGITS
     partner
    1.02
     partnering
    1.00
     partnership
    0.91
     partners
    0.88
    Partner
    0.86
     Partner
    0.85
    partner
    0.79
    Zimbabwe
    0.77
    解消
    0.77
     Partners
    0.77
    Activations Density 0.041%

    No Known Activations