© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22193
    Prev
    Next
    INDEX
    Explanations

    chemical groups ending in yl

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

    chemical compound structures and molecular groups in scientific/pharmaceutical text.

    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
    ↵↵↵
    -1.85
    ');
    -1.79
    archical
    -1.68
    ')
    -1.67
     También
    -1.64
    </h4>
    -1.63
     Of
    -1.63
    endpush
    -1.61
     nuevos
    -1.58
     Inoltre
    -1.55
    POSITIVE LOGITS
    )
    2.56
    ・・・・・・・・
    2.20
    ====
    2.11
    This
    2.09
    ~~~~
    2.05
     ↓
    2.02
     αυτή
    2.02
    Each
    2.02
    ーーーー
    1.95
     bestellt
    1.94
    Activations Density 0.077%

    No Known Activations