© 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. 72819
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and names

    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
     despi
    -1.55
     chemins
    -1.55
     courir
    -1.53
     uly
    -1.52
     Voilà
    -1.51
     besoins
    -1.47
    
    -1.43
     jezt
    -1.40
     ======
    -1.39
     bascul
    -1.38
    POSITIVE LOGITS
     to
    2.17
     one
    2.14
     as
    2.05
     in
    1.77
     at
    1.77
     just
    1.73
     by
    1.69
     two
    1.63
     still
    1.61
     an
    1.59
    Activations Density 0.119%

    No Known Activations