© 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. 25626
    Prev
    Next
    INDEX
    Explanations

    laboratory health safety precautions

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

    scientific or technical procedures in laboratory or testing contexts.

    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
    ktör
    -0.82
     interviews
    -0.81
     cómo
    -0.78
    nextProps
    -0.76
     Ainda
    -0.75
     mudança
    -0.73
     Mesmo
    -0.73
     Spazier
    -0.72
     devenue
    -0.71
    инг
    -0.71
    POSITIVE LOGITS
     riport
    1.00
     prepared
    0.98
     precautions
    0.98
     reported
    0.94
     prepare
    0.93
     Prepare
    0.93
     safety
    0.88
     report
    0.85
     Procedure
    0.85
    Prepare
    0.81
    Activations Density 0.006%

    No Known Activations