© 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. 33107
    Prev
    Next
    INDEX
    Explanations

    conveyor systems and convertibility

    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
     PRODUCTION
    -0.89
    perception
    -0.85
    podium
    -0.81
    IRES
    -0.77
    ṕ
    -0.75
    racks
    -0.75
     dispensing
    -0.75
    mity
    -0.73
    ूम
    -0.73
     samti
    -0.73
    POSITIVE LOGITS
     convic
    0.73
     لمس
    0.73
    Bakery
    0.72
     steeper
    0.71
    ']").
    0.71
    bParam
    0.70
    回报
    0.70
     MSI
    0.69
     bacter
    0.69
     carcass
    0.68
    Activations Density 0.024%

    No Known Activations