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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 25
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ς
    0.26
    ONS
    0.26
     qīng
    0.26
     врача
    0.25
    ﺘ
    0.25
    க்
    0.24
    ۔
    0.23
     paragraphe
    0.23
    ният
    0.23
    ព្យ
    0.23
    POSITIVE LOGITS
    an
    0.32
    ">&
    0.30
     Suriname
    0.29
    });
    0.29
    export
    0.28
           
    0.28
     Gaza
    0.28
             
    0.27
     Ruman
    0.27
     Congo
    0.27
    Activations Density 0.905%

    No Known Activations