© 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. 22-GEMMASCOPE-RES-131K
    7. 39337
    Prev
    Next
    INDEX
    Explanations

    medical imaging and procedures and treatments

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

    medical and technical terms related to viewing or examining something.

    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_22/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
    ツヤ
    -1.05
     gier
    -1.03
     certamente
    -1.02
    extAlignment
    -1.00
    Ive
    -1.00
     gefe
    -1.00
     София
    -0.96
    だけでなく
    -0.96
     casamento
    -0.95
     Czę
    -0.94
    POSITIVE LOGITS
     again
    2.03
     during
    1.56
     after
    1.52
     until
    1.45
     while
    1.44
     continues
    1.41
     continue
    1.40
     continued
    1.32
     remain
    1.31
     will
    1.30
    Activations Density 0.074%

    No Known Activations