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

    Neuronpedia

    Jacobian LensNEW
    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. 19312
    Prev
    Next
    INDEX
    Explanations

    GPT, LLMs, AI models

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

    capitalized proper nouns and acronyms denoting specific technical frameworks, AI/ML models, and formal regulatory filings or rules.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    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
     commencent
    0.38
     Wachstum
    0.38
    uración
    0.37
     Isaac
    0.36
    চ্ছু
    0.36
     Joseph
    0.35
     приблизи
    0.35
    রত
    0.34
     Lambert
    0.34
     länger
    0.34
    POSITIVE LOGITS
    Various
    0.55
    both
    0.55
    系列的
    0.54
    シリーズ
    0.48
     type
    0.47
     종류
    0.46
     시리즈
    0.46
     zarówno
    0.45
    Ⅱ
    0.45
    ทั้ง
    0.44
    Activations Density 0.247%

    No Known Activations