© 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. 56013
    Prev
    Next
    INDEX
    Explanations

    German titles, contrast, genetic studies

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

    document formatting elements like headers, section breaks, and content divisions in code or documentation files.

    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_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
    вшись
    -0.71
    嗜
    -0.71
     publisher
    -0.70
    útbol
    -0.69
     Mow
    -0.67
     saliva
    -0.66
    コム
    -0.65
     atsi
    -0.64
    価値
    -0.64
     clergyman
    -0.63
    POSITIVE LOGITS
     warehouse
    0.87
     stranded
    0.87
    razioni
    0.76
     Bill
    0.76
     warehouses
    0.75
    ูก
    0.74
    ального
    0.71
    🚛
    0.71
     warehousing
    0.71
    ggiato
    0.69
    Activations Density 0.000%

    No Known Activations