© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14945
    Prev
    Next
    INDEX
    Explanations

    political figures and government

    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
     now
    -1.70
     vêtement
    -1.27
     of
    -1.26
     this
    -1.26
     preferências
    -1.21
     különböző
    -1.20
    hichever
    -1.19
     tigre
    -1.17
     if
    -1.14
    cych
    -1.13
    POSITIVE LOGITS
     leurs
    1.33
     proporcionan
    1.30
     ancla
    1.28
     отсутствие
    1.26
     eases
    1.26
     juzg
    1.25
     images
    1.24
     puedan
    1.23
     aislado
    1.23
     realizan
    1.22
    Activations Density 0.256%

    No Known Activations