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. 11825
    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
     seperti
    0.94
     how
    0.93
    <unused2166>
    0.91
     like
    0.90
     violência
    0.87
     precum
    0.87
     violencia
    0.85
     cómo
    0.84
     como
    0.83
     hvordan
    0.83
    POSITIVE LOGITS
     (
    1.11
     (
    0.94
    (
    0.89
     ((
    0.78
     (#
    0.76
    init
    0.75
     (<
    0.72
    Begin
    0.69
    T
    0.69
    Start
    0.69
    Activations Density 0.004%

    No Known Activations