© 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. 90894
    Prev
    Next
    INDEX
    Explanations

    medical procedures and body parts

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

    specialized professional or technical terms, particularly in medical, scientific, and automotive fields.

    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
     
    -2.08
    の詳細
    -1.38
    に加
    -1.27
     Compañía
    -1.19
    assy
    -1.19
    からお
    -1.19
     milhões
    -1.18
     kuitenkin
    -1.16
    をチェック
    -1.16
     baixa
    -1.16
    POSITIVE LOGITS
     considerados
    1.45
    quarelle
    1.37
    ↵↵↵
    1.37
     理由
    1.35
    全是
    1.27
    몫
    1.27
     each
    1.23
    jaket
    1.23
     вторая
    1.23
     recordar
    1.22
    Activations Density 0.140%

    No Known Activations