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. 1178
    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
     yourself
    1.05
    }{
    1.00
    }
    0.99
     }
    0.97
    让你
    0.94
    )}
    0.92
    },
    0.90
    }:
    0.89
    }=$
    0.88
    )}$
    0.86
    POSITIVE LOGITS
     their
    4.53
     mereka
    4.01
    Their
    3.97
     Their
    3.96
    their
    3.94
     they
    3.87
     loro
    3.75
    他们的
    3.68
     leurs
    3.65
    他们
    3.63
    Activations Density 3.967%

    No Known Activations