© 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. 115700
    Prev
    Next
    INDEX
    Explanations

    margin and marginal terms

    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
    pagnols
    -0.95
    躥
    -0.91
    vices
    -0.89
    撾
    -0.88
    liseum
    -0.88
    pport
    -0.88
    MICHAEL
    -0.87
     grossa
    -0.87
     Puntos
    -0.86
     severa
    -0.86
    POSITIVE LOGITS
    margin
    1.48
     Margin
    1.24
     margin
    1.19
     marginal
    1.15
    marginal
    1.11
     waar
    1.03
     quicker
    1.02
     Marginal
    1.00
     new
    0.92
     brilliant
    0.92
    Activations Density 0.007%

    No Known Activations