© 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. 109621
    Prev
    Next
    INDEX
    Explanations

    automotive parts and applications

    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
     people
    -0.92
    طار
    -0.81
     nghỉ
    -0.80
    Customized
    -0.77
    Touches
    -0.77
     troll
    -0.77
    眺望
    -0.75
    Mechanics
    -0.73
    ンスター
    -0.72
    处理器
    -0.72
    POSITIVE LOGITS
    vehicle
    1.05
     APPLICATION
    1.05
    vestimento
    0.95
    vehicles
    0.95
    umacher
    0.94
     vehicle
    0.94
     INSTALLATION
    0.94
     INSTRUCTIONS
    0.94
    Radians
    0.94
    application
    0.93
    Activations Density 0.040%

    No Known Activations