© 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. 87405
    Prev
    Next
    INDEX
    Explanations

    present day contexts

    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
     fizeram
    -2.41
     tiveram
    -1.96
     ons
    -1.91
    狲
    -1.91
     komplette
    -1.80
    馓
    -1.80
    ᥬ
    -1.77
     préc
    -1.76
     tinham
    -1.73
     Verwenden
    -1.68
    POSITIVE LOGITS
     millioner
    2.36
     infierno
    2.11
     республики
    1.92
    c
    1.92
     wünsche
    1.90
    豋
    1.89
     totalCount
    1.89
     sophisticated
    1.87
     interestingly
    1.87
    冬季
    1.85
    Activations Density 0.003%

    No Known Activations