© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94002
    Prev
    Next
    INDEX
    Explanations

    machining operations

    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
     potrebbero
    -0.88
    çalves
    -0.82
     tools
    -0.76
     tool
    -0.75
     bitumen
    -0.75
    ASSESSMENT
    -0.73
     Felton
    -0.72
     professionale
    -0.71
     Gaff
    -0.71
    tool
    -0.69
    POSITIVE LOGITS
     machining
    1.23
    Operations
    1.09
     operations
    1.01
     Operations
    0.99
    ining
    0.98
     milling
    0.97
    加工
    0.92
     OPERATIONS
    0.91
     canned
    0.91
    operations
    0.90
    Activations Density 0.039%

    No Known Activations