© 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. 60620
    Prev
    Next
    INDEX
    Explanations

    manufacturer or brand

    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
    二郎
    -0.78
    angerie
    -0.77
    pair
    -0.76
     LCCN
    -0.74
    گرد
    -0.73
    mechanic
    -0.73
    ṛ
    -0.72
    magaz
    -0.71
    cto
    -0.71
    Pair
    -0.70
    POSITIVE LOGITS
     manufacturers
    4.88
     manufacturer
    4.81
     manufactures
    3.30
    manufacturer
    3.27
     Manufacturer
    3.19
     Manufacturers
    3.16
     fabricante
    3.08
    Manufacturer
    3.06
     fabricantes
    2.98
     manufacture
    2.95
    Activations Density 0.101%

    No Known Activations