© 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. 73949
    Prev
    Next
    INDEX
    Explanations

    Search Listings:

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    autoreleasepool
    -1.20
    のご紹介
    -1.13
    wanted
    -1.11
    ⁰
    -1.05
     планы
    -1.05
     eventi
    -1.00
    mogen
    -1.00
    varies
    -1.00
    vary
    -0.99
     perguntou
    -0.99
    POSITIVE LOGITS
     zuneh
    1.04
    Vak
    1.00
     блюдо
    0.94
    Curs
    0.93
     keineswegs
    0.92
    Kurs
    0.91
     Arrested
    0.90
     disgraced
    0.90
     Цвет
    0.89
     Compre
    0.88
    Activations Density 0.001%

    No Known Activations