© 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. 879
    Prev
    Next
    INDEX
    Explanations

    code delimiters or formatting

    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
     when
    -2.19
    </b>
    -2.05
     where
    -2.02
     before
    -1.99
     without
    -1.95
     just
    -1.64
     whose
    -1.63
    してきました
    -1.63
     which
    -1.63
     that
    -1.63
    POSITIVE LOGITS
     \{
    1.86
     ซึ่ง
    1.79
     มา
    1.74
    渽
    1.73
    GGGG
    1.73
     การ
    1.73
     :"
    1.70
     ที่
    1.70
    /}.
    1.69
     ruines
    1.66
    Activations Density 0.003%

    No Known Activations