© 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. 11980
    Prev
    Next
    INDEX
    Explanations

    Q: followed by numbers or reasons

    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
     predictor
    -0.77
     redefine
    -0.73
     prepaid
    -0.71
    actéristiques
    -0.71
     conditioning
    -0.70
     okhttp
    -0.70
    Răspunde
    -0.70
     település
    -0.69
    inkgo
    -0.68
     phénom
    -0.67
    POSITIVE LOGITS
     quadrature
    0.93
     aspect
    0.87
     Quad
    0.85
     quadrat
    0.82
    quad
    0.82
     tr
    0.81
     trigon
    0.81
    Quad
    0.79
     Mute
    0.79
    quartile
    0.78
    Activations Density 0.013%

    No Known Activations