© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14981
    Prev
    Next
    INDEX
    Explanations

    regulation, health, and economic terms

    np_acts-logits-general · gemini-2.5-flash-lite

    words and phrases related to economic, financial, and healthcare systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     duquel
    -1.61
     geringe
    -1.61
     ponts
    -1.58
     voer
    -1.54
     strategie
    -1.52
     û
    -1.51
     appartement
    -1.50
     noten
    -1.50
     behand
    -1.48
     issus
    -1.48
    POSITIVE LOGITS
     Actually
    1.91
     in
    1.88
     might
    1.73
     Those
    1.71
     before
    1.71
     may
    1.70
     Before
    1.69
     Unlike
    1.67
    Those
    1.63
     or
    1.60
    Activations Density 0.124%

    No Known Activations