© 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. 90964
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and materials

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

    chemical compounds and scientific terminology related to chemical structures, particularly phosphates, esters, and other chemical suffixes like -ate, -ine, and -ide.

    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
    を入れる
    -0.88
    ホント
    -0.81
     Oxide
    -0.79
     silic
    -0.79
    今も
    -0.77
     Retrieves
    -0.77
     diligen
    -0.76
     Closes
    -0.75
    вање
    -0.75
    頜
    -0.75
    POSITIVE LOGITS
     honlap
    0.91
    姒
    0.90
    сва
    0.90
     solution
    0.89
     ($\
    0.88
     denim
    0.83
     famosos
    0.81
    合物
    0.81
    FormBuilder
    0.81
     chyba
    0.81
    Activations Density 0.181%

    No Known Activations