© 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. 80600
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    technical or specialized terminology from various fields including medicine, programming, and scientific domains.

    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
     applau
    -1.61
     investir
    -1.61
    都沒有
    -1.47
    縵
    -1.42
     concluye
    -1.42
     sorprende
    -1.41
     europé
    -1.40
     merveilleux
    -1.38
     conster
    -1.38
     vengo
    -1.36
    POSITIVE LOGITS
     on
    1.98
     is
    1.61
     also
    1.57
     you
    1.56
    tonsoft
    1.45
    ordat
    1.44
     diese
    1.39
     questi
    1.32
     deze
    1.30
     кно
    1.30
    Activations Density 0.239%

    No Known Activations