© 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. 91054
    Prev
    Next
    INDEX
    Explanations

    private attorneys general

    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
     rapport
    -0.88
     deste
    -0.77
    ನ್ನು
    -0.73
    ophytes
    -0.73
     muda
    -0.72
    tobe
    -0.70
     мә
    -0.70
     overall
    -0.70
     artistas
    -0.69
     arbitration
    -0.69
    POSITIVE LOGITS
    PRIVATE
    1.23
     private
    1.20
     civil
    1.11
     Injured
    1.10
    private
    1.10
    ACTION
    1.06
    Private
    1.05
     suits
    1.04
     wronged
    1.04
     aggrieved
    1.02
    Activations Density 0.051%

    No Known Activations