© 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. 10-GEMMASCOPE-RES-131K
    7. 69385
    Prev
    Next
    INDEX
    Explanations

    finance, investors, currency

    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_10/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
     multicolore
    -1.73
     religieux
    -1.60
     autonomie
    -1.53
     włosów
    -1.46
     vernis
    -1.39
     प्रोड
    -1.39
     décret
    -1.38
     constamment
    -1.38
     brune
    -1.37
     intrig
    -1.35
    POSITIVE LOGITS
     from
    1.53
     for
    1.47
     both
    1.42
     pre
    1.35
     will
    1.35
     against
    1.30
     before
    1.29
     without
    1.26
    ִּ
    1.22
     राज्य
    1.20
    Activations Density 0.029%

    No Known Activations