© 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. 81444
    Prev
    Next
    INDEX
    Explanations

    types of equipment

    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
     งาน
    -0.86
    زیین
    -0.79
     {?>
    -0.77
    igrette
    -0.77
    ńskiego
    -0.76
    ASKET
    -0.73
     /><
    -0.71
    shirt
    -0.71
    主教
    -0.71
     conse
    -0.71
    POSITIVE LOGITS
     equipment
    6.53
    equipment
    4.59
    Equipment
    4.09
     Equipment
    4.03
     EQUIPMENT
    3.83
     machinery
    3.41
    EQUIPMENT
    3.38
     equipments
    3.17
     equipamentos
    3.02
    设备
    2.91
    Activations Density 0.164%

    No Known Activations