© 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. 94106
    Prev
    Next
    INDEX
    Explanations

    chemicals and regulations

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

    scientific or technical terms related to chemicals and materials.

    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
     SGD
    -0.87
    tyard
    -0.75
     Marathi
    -0.73
     vícti
    -0.73
    oyo
    -0.72
     transfusion
    -0.72
     Marquette
    -0.71
     Fondation
    -0.71
    ógy
    -0.71
     yard
    -0.70
    POSITIVE LOGITS
    TSCA
    1.20
     HPV
    1.09
     tonnage
    0.95
     Chemical
    0.92
     chemicals
    0.86
    DSL
    0.83
    EIN
    0.83
    Sponsor
    0.82
     Inventory
    0.81
    症
    0.79
    Activations Density 0.017%

    No Known Activations