© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101249
    Prev
    Next
    INDEX
    Explanations

    carbonyl and CO in chemical contexts

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

    chemical terms containing "carbonyl" and carbon monoxide (CO) in scientific documents.

    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_10/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
     estí
    -1.70
     myriad
    -1.66
    樒
    -1.65
     it
    -1.63
     requerimientos
    -1.63
    廔
    -1.62
    ⽽
    -1.59
     folhe
    -1.59
    絎
    -1.56
    ){$
    -1.55
    POSITIVE LOGITS
    0
    2.70
    </strong>
    2.11
    ”،
    1.75
     Lø
    1.64
    </
    1.58
    </h3>
    1.52
     any
    1.52
    When
    1.50
    我们
    1.49
     unholy
    1.49
    Activations Density 0.012%

    No Known Activations