© 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. 22-GEMMASCOPE-RES-131K
    7. 15819
    Prev
    Next
    INDEX
    Explanations

    plot and graph

    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_22/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
     getItemId
    -0.96
    模特
    -0.91
    ْم
    -0.90
     zult
    -0.89
     ricordi
    -0.88
     preghi
    -0.87
    outros
    -0.86
     bianche
    -0.85
     yoktur
    -0.84
    IModel
    -0.84
    POSITIVE LOGITS
     diagram
    1.18
     plot
    1.15
     graph
    1.12
     trend
    1.07
     curves
    1.05
     matplotlib
    1.04
    plot
    1.01
    Diagram
    0.98
     verschiedene
    0.97
     plotted
    0.95
    Activations Density 0.051%

    No Known Activations