© 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. 119130
    Prev
    Next
    INDEX
    Explanations

    financial institutions, markets, crisis

    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
     éton
    -0.77
     responde
    -0.77
    chowy
    -0.74
     Sill
    -0.74
     Ucraina
    -0.73
    ℍ
    -0.72
     feito
    -0.71
    Via
    -0.71
     கூ
    -0.70
    ඛ
    -0.70
    POSITIVE LOGITS
     sector
    1.02
     markets
    1.02
     market
    0.94
    market
    0.94
     soundness
    0.83
    markets
    0.76
     system
    0.75
     市场
    0.75
    orianCalendar
    0.70
    marginBottom
    0.68
    Activations Density 0.029%

    No Known Activations