© 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. 33098
    Prev
    Next
    INDEX
    Explanations

    Guangdong, dilated CBD, carrot

    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
    ธิ
    -0.82
    📐
    -0.81
     Mahomet
    -0.81
     Shropshire
    -0.79
     Sikkim
    -0.78
     Knob
    -0.77
     Gutenberg
    -0.77
     Shandong
    -0.75
     buckwheat
    -0.74
    ágina
    -0.74
    POSITIVE LOGITS
     Guangzhou
    1.41
     Guangdong
    1.26
     Cantonese
    1.16
    Alabama
    1.04
    Atlanta
    1.03
    Florida
    1.02
     Canton
    1.00
    Tampa
    0.98
    Mississippi
    0.96
    Miami
    0.93
    Activations Density 0.031%

    No Known Activations