© 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. 90549
    Prev
    Next
    INDEX
    Explanations

    proprietary drugs and databases

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

    numbers, numeric data, and statistical values in pharmaceutical and biotech industry articles.

    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
    Melhor
    -0.71
    ニー
    -0.68
     Sum
    -0.68
    ɰ
    -0.65
    ณา
    -0.65
     Individual
    -0.64
     buttery
    -0.64
    ṃ
    -0.63
    Mejor
    -0.62
    decap
    -0.62
    POSITIVE LOGITS
     congratulations
    0.88
     סי
    0.79
     [+
    0.78
    了一口
    0.77
    nocześnie
    0.77
    robial
    0.76
    empt
    0.75
    want
    0.75
     ſi
    0.75
    TextSpan
    0.74
    Activations Density 0.012%

    No Known Activations