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. 1198
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the assistant's discourse-opening phrases that begin explanations or step‑by‑step guides (e.g., "Okay, let's break down", "Here's a ... guide").

    oai_token-act-pair · gpt-5-miniTriggered by @toaster
    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
    ...(
    0.82
     (...
    0.79
     ...(
    0.77
    Pss
    0.74
     (_
    0.71
     (...)
    0.71
    :(
    0.71
     ----------
    0.70
     Listen
    0.70
     pause
    0.70
    POSITIVE LOGITS
     ஒன்றாகும்
    0.80
    dasarkan
    0.77
     schöne
    0.76
     correctamente
    0.76
     katika
    0.73
     사용하는
    0.73
     dalam
    0.71
    !),
    0.71
    將
    0.71
    ệt
    0.71
    Activations Density 0.556%

    No Known Activations