© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 353
    Prev
    Next
    INDEX
    Explanations

    foreign words and nature descriptions

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

    descriptions of nature and outdoor experiences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ּוֹ
    -1.88
    ַּ
    -1.75
    ᾿
    -1.51
     tevreden
    -1.48
     موبایل
    -1.47
    ִּ
    -1.46
    וּ
    -1.40
     чехол
    -1.37
    ֶּ
    -1.37
    修为
    -1.35
    POSITIVE LOGITS
    ׇ
    1.75
    อร่อย
    1.54
     ингреди
    1.52
     النبات
    1.45
     cukru
    1.45
     ویتامین
    1.41
    ֺ
    1.38
    ocarc
    1.36
     skóry
    1.33
     الماء
    1.33
    Activations Density 0.053%

    No Known Activations