© 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. 90474
    Prev
    Next
    INDEX
    Explanations

    "the" + area/region

    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
     geschehen
    -0.87
    kungen
    -0.86
    🏸
    -0.85
    ᪥
    -0.85
     irgendwo
    -0.85
     commerciales
    -0.84
    ustes
    -0.83
    ウダー
    -0.82
    تمع
    -0.82
     chacune
    -0.81
    POSITIVE LOGITS
     area
    5.84
    area
    3.94
     region
    3.53
    Area
    3.34
     området
    3.16
     المنطقة
    3.16
     AREA
    3.13
     Area
    3.11
     área
    3.09
    AREA
    2.91
    Activations Density 0.071%

    No Known Activations