© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70283
    Prev
    Next
    INDEX
    Explanations

    introducing contrast or exception

    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_10/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
    Transkript
    -1.49
    :
    -1.49
     caused
    -1.39
     clientèle
    -1.34
     when
    -1.31
     consequently
    -1.31
     gradually
    -1.30
     then
    -1.28
     allows
    -1.27
     Then
    -1.26
    POSITIVE LOGITS
    erda
    1.55
     you
    1.37
    lho
    1.36
    cursions
    1.36
     artigos
    1.34
     allerdings
    1.34
    
    1.34
    vaders
    1.33
     nouvelles
    1.32
    erii
    1.31
    Activations Density 0.089%

    No Known Activations