© 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. 34-GEMMASCOPE-RES-131K
    7. 996
    Prev
    Next
    INDEX
    Explanations

    barrister chambers

    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
     melodies
    -0.77
    陕西
    -0.75
     Cycle
    -0.75
    ナルド
    -0.72
    æus
    -0.71
    собенно
    -0.70
    derabad
    -0.69
    >::
    -0.69
    Cycle
    -0.68
     Rong
    -0.68
    POSITIVE LOGITS
     barrister
    1.10
     chambers
    1.10
    Temple
    0.92
     Chambers
    0.80
    bar
    0.80
    inigungs
    0.78
     Bar
    0.77
    Bar
    0.77
     Temple
    0.75
    ಆ
    0.75
    Activations Density 0.031%

    No Known Activations