© 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. 90425
    Prev
    Next
    INDEX
    Explanations

    Mercedes-Benz and chemical compounds

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

    chemical compound names containing "benz" or "Benz" (like benzofuran, benzene, Mercedes-Benz).

    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
    en
    -2.72
     A
    -2.50
    ie
    -2.47
     вашем
    -2.36
     relentless
    -2.36
     lose
    -2.34
     estimé
    -2.33
     So
    -2.20
    
    -2.14
    为了
    -2.11
    POSITIVE LOGITS
     reinigen
    2.48
    ﺢ
    2.41
    A
    2.28
    獁
    2.28
    𓆜
    2.27
     rito
    2.25
    ＝＝＝＝
    2.25
     verminder
    2.22
    ودر
    2.20
    　＊
    2.20
    Activations Density 0.004%

    No Known Activations