© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84377
    Prev
    Next
    INDEX
    Explanations

    diagnosing postoperative meningitis

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

    triple quotes (''') used for Python docstrings.

    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
    ))}
    -1.41
    ...</
    -1.38
    UGHTER
    -1.33
    悲伤
    -1.33
    相似
    -1.30
                                
    -1.23
    ți
    -1.23
    ซึ่ง
    -1.21
    ține
    -1.20
    ximadamente
    -1.17
    POSITIVE LOGITS
     Moreover
    1.41
    ?
    1.39
     Nevertheless
    1.33
     Instead
    1.28
     Sì
    1.27
     divisa
    1.26
     Además
    1.25
     marea
    1.25
    ‍♂
    1.23
     decidi
    1.23
    Activations Density 0.200%

    No Known Activations