© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104120
    Prev
    Next
    INDEX
    Explanations

    multi-drug resistance phenotype

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

    technical identifiers like MDR (multi-drug resistance) and unordered_map.

    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
    ]
    -2.66
    ſten
    -2.53
    ഀ
    -2.52
     ſch
    -2.44
     выборе
    -2.27
     ausein
    -2.25
     mußte
    -2.16
    🪤
    -2.14
     bobina
    -2.14
     $_=
    -2.13
    POSITIVE LOGITS
    re
    2.88
    $,
    2.64
    .
    2.59
    ’
    2.44
     entice
    2.33
     зона
    2.33
     They
    2.33
    de
    2.31
     Of
    2.28
    ’,
    2.28
    Activations Density 0.003%

    No Known Activations