© 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. 34-GEMMASCOPE-RES-131K
    7. 84959
    Prev
    Next
    INDEX
    Explanations

    oxygen transfer

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

    non-English characters and special letters from various languages.

    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_34/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
    盖
    -0.79
    ault
    -0.75
     negócio
    -0.73
    tigkeiten
    -0.73
     grit
    -0.73
     क्ल
    -0.72
     visible
    -0.71
    ၊
    -0.70
     Podcast
    -0.70
     exist
    -0.69
    POSITIVE LOGITS
    テレ
    0.81
     irré
    0.74
     Oxidation
    0.74
     uve
    0.73
     奥
    0.73
     appliquer
    0.72
     automóviles
    0.72
    matching
    0.71
     Tento
    0.71
     gydy
    0.71
    Activations Density 0.036%

    No Known Activations