© 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. 10047
    Prev
    Next
    INDEX
    Explanations

    business entities or functions

    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
    ཥ
    -2.09
     the
    -1.91
    ➀
    -1.90
    嗱
    -1.87
    橼
    -1.85
     ――
    -1.80
    Which
    -1.80
    㩒
    -1.78
    which
    -1.77
     vixion
    -1.73
    POSITIVE LOGITS
    1
    2.05
     if
    1.99
     also
    1.95
     its
    1.90
     suoi
    1.88
     requires
    1.78
     additional
    1.75
    它
    1.73
     terribly
    1.73
     includes
    1.73
    Activations Density 0.332%

    No Known Activations