© 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. 58047
    Prev
    Next
    INDEX
    Explanations

    defending champion

    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
     brady
    -0.90
     when
    -0.85
    eder
    -0.81
     fluxes
    -0.79
    Appellee
    -0.77
     it
    -0.75
    ppan
    -0.75
     variasi
    -0.75
    незон
    -0.75
    逮捕
    -0.74
    POSITIVE LOGITS
     reigning
    3.78
     defending
    3.75
    Reign
    2.33
    reign
    2.22
     defend
    2.13
     defends
    1.92
     Reign
    1.88
     last
    1.79
     current
    1.75
     vigente
    1.75
    Activations Density 0.078%

    No Known Activations