© 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. 50174
    Prev
    Next
    INDEX
    Explanations

    made in USA

    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
    ({
    -0.78
    Disney
    -0.78
    чества
    -0.77
    Ꭱ
    -0.76
    TInt
    -0.75
    В
    -0.75
    ꒰
    -0.73
    Houston
    -0.73
    {-
    -0.73
    ([
    -0.73
    POSITIVE LOGITS
     Made
    3.22
    Made
    2.92
     made
    2.86
     MADE
    2.59
    MADE
    2.56
    made
    2.50
     manufactured
    2.50
     produced
    2.25
     Manufactured
    1.91
     manufacturing
    1.88
    Activations Density 0.038%

    No Known Activations