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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 153
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-1b-it/resid_post
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     O
    0.76
     prevent
    0.73
     U
    0.72
     N
    0.70
     ț
    0.69
     same
    0.67
     allow
    0.67
     T
    0.67
     specify
    0.66
     other
    0.66
    POSITIVE LOGITS
    ```
    0.76
    Investing
    0.72
    <end_of_image>
    0.70
    Investment
    0.69
    的可能性
    0.66
    する方法
    0.65
    Invest
    0.65
    Effect
    0.65
    https
    0.64
    So
    0.64
    Activations Density 4.729%

    No Known Activations