© 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. 10-GEMMASCOPE-RES-131K
    7. 70495
    Prev
    Next
    INDEX
    Explanations

    chemical analysis and compounds

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

    chemistry-related terms and concepts 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_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
     también
    -1.26
    Diwedd
    -1.26
     debería
    -1.26
     também
    -1.20
    itarias
    -1.16
    
    -1.12
     также
    -1.11
     todavía
    -1.11
    istici
    -1.11
     aquí
    -1.10
    POSITIVE LOGITS
    它們
    1.12
     ソース
    1.06
    IfExists
    1.04
    titia
    1.03
     選択
    1.02
     aligns
    1.02
     arrivato
    1.02
     bisogno
    1.01
     ramb
    1.01
     bisog
    1.00
    Activations Density 0.053%

    No Known Activations