© 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. 48087
    Prev
    Next
    INDEX
    Explanations

    trade union, trade name, trademark

    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
    ḑ
    -0.87
    ächtige
    -0.85
    我们要
    -0.80
    ρο
    -0.79
    udades
    -0.77
     recognizing
    -0.76
    𝒌
    -0.74
    経営
    -0.72
     dře
    -0.71
     lidé
    -0.70
    POSITIVE LOGITS
     trade
    1.53
    trade
    1.46
    Trade
    1.24
     Trade
    1.20
    offs
    1.13
    winds
    1.12
    marked
    1.08
    craft
    1.07
    off
    1.07
     TRADE
    1.02
    Activations Density 0.008%

    No Known Activations