© 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. 90790
    Prev
    Next
    INDEX
    Explanations

    Johns Hopkins, bisabolane, multiple, Poké Ball, Type, garden

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

    the beginning of technical or informational entries, particularly titles, headings, or first words of definitions.

    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
    .
    -2.03
     a
    -1.96
    是怎么回事
    -1.83
    男主
    -1.81
     壁纸
    -1.66
    지만
    -1.66
     nejsou
    -1.65
    诅
    -1.64
    年は
    -1.63
    -1.63
    POSITIVE LOGITS
     that
    2.45
     or
    1.98
     how
    1.92
     where
    1.88
     of
    1.88
    (!__
    1.80
     cueva
    1.79
     if
    1.78
     granja
    1.77
    öbb
    1.75
    Activations Density 4.724%

    No Known Activations