© 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. 98339
    Prev
    Next
    INDEX
    Explanations

    HTML URLs

    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
     if
    -1.63
     how
    -1.37
    閲覧
    -1.23
    その
    -1.22
    ๒
    -1.20
     out
    -1.16
    )
    
    -1.16
    </h3>
    -1.13
    <bos>
    -1.10
     вход
    -1.10
    POSITIVE LOGITS
    的味道
    1.33
    迨
    1.31
     zowel
    1.24
     umgeben
    1.24
     bijvoorbeeld
    1.22
     prácticamente
    1.22
     beispielsweise
    1.21
     Поэтому
    1.20
    中略
    1.18
    鷂
    1.18
    Activations Density 0.009%

    No Known Activations