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. 583
    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
     true
    0.71
     in
    0.68
     or
    0.65
     context
    0.65
     (
    0.63
     money
    0.62
     win
    0.61
     and
    0.60
     logic
    0.60
     you
    0.59
    POSITIVE LOGITS
    3
    1.37
    2
    1.30
    1
    1.23
    4
    1.22
    5
    1.18
    8
    1.18
    6
    1.16
    7
    1.14
    approx
    1.14
    9
    1.00
    Activations Density 1.427%

    No Known Activations