© 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. 34-GEMMASCOPE-RES-131K
    4. 115819
    Prev
    Next
    INDEX
    Explanations

    technoscientific and medical jargon

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

    programming and technical content like code, database entries, and scientific text.

    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
     bond
    -0.79
    bond
    -0.78
     Bond
    -0.71
    ่าน
    -0.68
    cultures
    -0.66
    票房
    -0.65
     прось
    -0.65
     stormwater
    -0.64
     nghiệm
    -0.63
    𝗷
    -0.63
    POSITIVE LOGITS
    時計
    0.70
     учреждения
    0.67
     kereta
    0.64
    giau
    0.63
    僚
    0.62
     дов
    0.61
    ュー
    0.61
    PES
    0.60
     amminist
    0.60
     دخ
    0.60
    Activations Density 0.082%

    No Known Activations