© 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. 87192
    Prev
    Next
    INDEX
    Explanations

    statutory bodies

    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
     '',
    -1.40
     ''
    -1.36
    ricanes
    -1.27
    minister
    -1.23
    ',
    -1.23
    often
    -1.22
     '#
    -1.21
     indien
    -1.18
     '
    -1.18
     chimie
    -1.17
    POSITIVE LOGITS
     will
    3.09
     it
    1.81
     our
    1.78
     that
    1.69
     what
    1.61
     volontà
    1.54
     these
    1.49
     vicenda
    1.43
     yesterday
    1.43
    它
    1.40
    Activations Density 0.100%

    No Known Activations