© 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. 116376
    Prev
    Next
    INDEX
    Explanations

    metallurgical processes and pulp processing

    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
    琥
    -0.76
     intercooler
    -0.73
    ционных
    -0.69
    Дина
    -0.69
     کیا
    -0.68
    れてる
    -0.68
    Suppl
    -0.68
    resiasi
    -0.68
     Zucker
    -0.67
    магазин
    -0.67
    POSITIVE LOGITS
     flotation
    1.20
     pulp
    1.02
     concentrate
    0.99
     liberation
    0.95
     recoveries
    0.94
     circuits
    0.93
    grind
    0.87
    Locked
    0.85
     recovery
    0.85
     circuit
    0.85
    Activations Density 0.048%

    No Known Activations