© 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. 82466
    Prev
    Next
    INDEX
    Explanations

    cross-linking

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

    terms related to chemical cross-linking in scientific contexts, particularly in hydrogel and polymer 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
    гно
    -0.70
    ksin
    -0.69
     сов
    -0.66
     montagem
    -0.65
     separator
    -0.65
    合作伙伴
    -0.64
     sortBy
    -0.64
    [:,
    -0.64
    Relief
    -0.63
    ίδ
    -0.63
    POSITIVE LOGITS
     cross
    2.98
    cross
    2.36
    Cross
    2.17
     Cross
    2.17
    CROSS
    2.05
     CROSS
    1.99
    クロス
    1.40
    交叉
    1.40
    linking
    1.31
     links
    1.29
    Activations Density 0.138%

    No Known Activations