© 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. 85272
    Prev
    Next
    INDEX
    Explanations

    foreign language and specific 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
    鹩
    -1.71
    trying
    -1.55
    wonderful
    -1.55
    “”
    -1.54
    specifically
    -1.51
    artigen
    -1.49
     accompag
    -1.49
    lovely
    -1.48
    several
    -1.47
     soucis
    -1.47
    POSITIVE LOGITS
     not
    2.19
     only
    2.19
     Surprisingly
    1.95
     less
    1.92
     first
    1.90
     did
    1.89
     without
    1.87
     all
    1.84
     more
    1.84
     in
    1.83
    Activations Density 0.028%

    No Known Activations