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. 8478
    Prev
    Next
    INDEX
    Explanations

    science and scientists

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

    academic and scientific content related to research publications, universities, and scholarly activities.

    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
    ācijas
    -0.78
    єдна
    -0.77
     CDN
    -0.74
     ITV
    -0.74
     classmates
    -0.73
    ﯽ
    -0.73
    ፈ
    -0.73
     Tré
    -0.72
     Pág
    -0.71
    際は
    -0.71
    POSITIVE LOGITS
     misconduct
    1.21
     scientific
    1.16
     Scientific
    1.14
     scientists
    1.12
     Science
    1.11
     Sci
    1.11
     science
    1.09
    Science
    1.05
     нау
    1.05
     Scientists
    1.03
    Activations Density 0.064%

    No Known Activations