© 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. 34-GEMMASCOPE-RES-131K
    4. 25792
    Prev
    Next
    INDEX
    Explanations

    biotech and pharma companies

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

    company names in the biotech/pharmaceutical industry.

    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
     chré
    -0.85
    ᧐
    -0.81
     ört
    -0.81
     textile
    -0.79
     клиентов
    -0.78
    aic
    -0.77
     parametros
    -0.76
     inland
    -0.76
    .+\
    -0.76
    图为
    -0.75
    POSITIVE LOGITS
     drug
    1.34
     Therapeutics
    1.29
    vartis
    1.21
     pharma
    1.19
     biotech
    1.17
    drug
    1.16
    pharma
    1.10
    onucleotides
    1.08
    Drug
    1.08
     scientific
    1.08
    Activations Density 0.055%

    No Known Activations