Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8428
    Prev
    Next
    INDEX
    Explanations

    medical issues or conditions

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

    medical case reports and clinical descriptions of patient symptoms and conditions.

    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
     家具
    -1.22
     katun
    -1.09
     preventative
    -1.09
     ekst
    -1.07
     العديد
    -1.05
     كيفية
    -1.05
     ケ
    -1.03
    typically
    -1.02
     Ō
    -1.02
     cewek
    -1.01
    POSITIVE LOGITS
    
    1.60
     commonest
    1.24
     meticulous
    1.16
     meticulously
    1.15
     till
    1.05
     upto
    1.02
     gives
    1.01
     got
    1.00
     wrongly
    1.00
     gave
    1.00
    Activations Density 0.410%

    No Known Activations