© 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. 33696
    Prev
    Next
    INDEX
    Explanations

    drug action modulation

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

    scientific terminology related to pharmacology and neuroscience research.

    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
     artículos
    -0.85
    她也
    -0.84
     nochmal
    -0.82
     negócios
    -0.82
    țiilor
    -0.81
     Produkten
    -0.80
     لباس
    -0.79
    erci
    -0.78
    ERNES
    -0.78
    verage
    -0.77
    POSITIVE LOGITS
    信頼
    0.90
     abolished
    0.88
     effects
    0.88
     blockade
    0.87
     equip
    0.87
    ceiling
    0.86
     pretreatment
    0.86
    Ceiling
    0.81
     drug
    0.80
    Bibliografia
    0.79
    Activations Density 0.907%

    No Known Activations