© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 24043
    Prev
    Next
    INDEX
    Explanations

    scientific data compilations and databases

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

    academic or scientific terms related to databases, catalogs, and datasets.

    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
    坶
    -1.79
    ೢ
    -1.77
    暃
    -1.67
    絝
    -1.67
    ౬
    -1.66
    蘩
    -1.66
    ୬
    -1.64
    ícias
    -1.59
    螣
    -1.53
     преимущества
    -1.51
    POSITIVE LOGITS
     for
    2.48
     by
    1.86
     providing
    1.41
     there
    1.41
     some
    1.36
     समी
    1.35
     Since
    1.34
     provided
    1.34
     many
    1.30
     numerous
    1.30
    Activations Density 0.109%

    No Known Activations