© 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. 10169
    Prev
    Next
    INDEX
    Explanations

    platin-based chemotherapy drugs

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

    proper names of people, scientific compounds, or brand names.

    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
    闥
    -2.94
      “
    -2.75
    隄
    -2.63
    x
    -2.52
    躝
    -2.50
    Many
    -2.42
     matelas
    -2.42
     maquillage
    -2.41
    结语
    -2.41
     seconde
    -2.41
    POSITIVE LOGITS
     $^{\
    2.95
    </strong>
    2.64
    ৄ
    2.63
    蜮
    2.53
     Importantly
    2.47
    ,"
    2.44
     그는
    2.44
     verknüp
    2.42
     AFTER
    2.42
    </em>
    2.42
    Activations Density 0.053%

    No Known Activations