© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6306
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite

    markers that signal the start of a response or section, such as headings, title-like phrases, and conversational openers indicating new content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مذکور
    0.32
     प्रदान
    0.31
     correspondingly
    0.30
     specifying
    0.30
     ተጨማሪ
    0.30
     ಮಾಹಿತಿ
    0.29
     উক্ত
    0.29
    提供
    0.29
     tersebut
    0.29
     उक्त
    0.29
    POSITIVE LOGITS
    dyž
    0.35
    story
    0.34
     raccont
    0.34
    Story
    0.32
     pięk
    0.31
     ज़िंदगी
    0.31
    spirational
    0.30
     racconto
    0.30
     你
    0.29
    fect
    0.29
    Activations Density 0.424%

    No Known Activations