© 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. 105953
    Prev
    Next
    INDEX
    Explanations

    benzodiazepine and names like Felipe

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

    names of pharmaceutical drugs and compounds, particularly benzodiazepines.

    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
    ኧ
    -3.09
    ﮭ
    -2.84
     内衣
    -2.78
    l
    -2.66
     nimmer
    -2.59
    ㌘
    -2.53
    ⸎
    -2.53
     バッジ
    -2.50
     Identifying
    -2.47
    鉿
    -2.39
    POSITIVE LOGITS
    ?’
    2.75
    which
    2.55
    してます
    2.47
    -
    2.30
    re
    2.30
    儼
    2.27
    ть
    2.23
    汌
    2.23
     wich
    2.22
     Италии
    2.16
    Activations Density 0.020%

    No Known Activations