© 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. 10-GEMMASCOPE-RES-131K
    4. 68987
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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_10/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
     принад
    -1.35
    $_.
    -1.31
     люб
    -1.28
    Quran
    -1.27
     blusas
    -1.27
     незавер
    -1.26
     Thier
    -1.22
    expiresIn
    -1.21
    zionamento
    -1.21
    šky
    -1.21
    POSITIVE LOGITS
    		
    1.48
     сообщили
    1.38
     такого
    1.36
     gestione
    1.34
    total
    1.30
     обору
    1.27
    んでる
    1.24
     вторая
    1.23
     большого
    1.23
     сайты
    1.21
    Activations Density 0.011%

    No Known Activations