© 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. 9924
    Prev
    Next
    INDEX
    Explanations

    quantities and concentrations

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

    numeric values and measurements in scientific papers, particularly percentages and decimal numbers.

    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
     if
    -1.52
    還有
    -1.49
     najdete
    -1.48
    颯
    -1.48
     robić
    -1.46
    鸲
    -1.41
    还有
    -1.41
     многих
    -1.40
    пыт
    -1.38
    每个
    -1.36
    POSITIVE LOGITS
     of
    1.95
     from
    1.38
     useRouter
    1.35
     زاده
    1.30
     the
    1.29
     ayaa
    1.26
     RSITY
    1.23
     albero
    1.23
    酲
    1.20
     such
    1.20
    Activations Density 0.080%

    No Known Activations