© 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. 124663
    Prev
    Next
    INDEX
    Explanations

    Epstein-Barr virus (EBV)

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

    stock ticker symbols and company names in parentheses, particularly in financial or medical contexts.

    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
     the
    -1.85
     either
    -1.85
     a
    -1.77
    鮰
    -1.72
    凄く
    -1.68
     kunne
    -1.66
     each
    -1.66
     quatre
    -1.63
     endast
    -1.63
     largely
    -1.59
    POSITIVE LOGITS
    .
    2.05
    您
    1.60
    There
    1.59
    You
    1.58
    Other
    1.57
     cappuccio
    1.52
     میکنه
    1.50
    žiaga
    1.48
     and
    1.45
    ähkö
    1.45
    Activations Density 0.081%

    No Known Activations