© 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. 38980
    Prev
    Next
    INDEX
    Explanations

    economic and financial indicators

    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
     what
    -1.62
    ashqai
    -1.57
     if
    -1.57
     when
    -1.54
     restaurantes
    -1.52
    voer
    -1.52
    大家都
    -1.50
    .~\
    -1.50
    casian
    -1.47
     who
    -1.45
    POSITIVE LOGITS
     rate
    1.62
     thingy
    1.55
    อื่น
    1.55
     overall
    1.47
     mantenerse
    1.42
     mostrarse
    1.41
     incl
    1.40
          
    1.36
     нового
    1.33
     ratio
    1.31
    Activations Density 0.051%

    No Known Activations