© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 925
    Prev
    Next
    INDEX
    Explanations

    Wall art, legislative assemblies, math problems

    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
     cães
    -1.74
     réjou
    -1.73
     étroite
    -1.69
     nowa
    -1.66
     Você
    -1.66
     firmy
    -1.65
     suivantes
    -1.63
    嗗
    -1.63
     juſ
    -1.63
    -¡
    -1.62
    POSITIVE LOGITS
     not
    2.28
     will
    2.28
     only
    2.14
     this
    2.08
    ↵↵
    1.96
    }{
    1.96
     in
    1.95
    </em>
    1.92
     even
    1.89
     has
    1.86
    Activations Density 0.040%

    No Known Activations