© 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. 83158
    Prev
    Next
    INDEX
    Explanations

    chemical agents and selectors

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

    chemical compounds, reagents, and catalysts in scientific texts.

    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
    </em>
    -0.92
    过程
    -0.85
     various
    -0.85
    第三方
    -0.84
    怎样的
    -0.83
    زیین
    -0.82
     از
    -0.82
     của
    -0.82
     countless
    -0.81
    ू
    -0.81
    POSITIVE LOGITS
     molecules
    1.23
     ajuta
    1.09
    鱂
    0.99
     candidates
    0.98
    Ҡ
    0.95
     chemicals
    0.93
     adicionar
    0.93
     molecule
    0.92
     capable
    0.90
    ffion
    0.90
    Activations Density 0.263%

    No Known Activations