© 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. 39361
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by context

    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
    blurRadius
    -1.64
    ↵↵
    -1.64
    LETIN
    -1.50
     для
    -1.48
     you
    -1.43
    $
    -1.39
     your
    -1.38
    }));
    -1.38
    ).
    -1.34
    。
    -1.34
    POSITIVE LOGITS
    tividade
    1.43
     bonté
    1.27
    的话
    1.26
    異なります
    1.22
    Часть
    1.20
     are
    1.16
     aband
    1.16
     pousser
    1.15
     बिंदु
    1.15
     dépenses
    1.15
    Activations Density 0.292%

    No Known Activations