© 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. 66027
    Prev
    Next
    INDEX
    Explanations

    strategy games and esports

    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
     veder
    -1.44
     decorativo
    -1.43
    genen
    -1.41
    čiu
    -1.41
     densidad
    -1.38
     dommages
    -1.38
     défauts
    -1.36
    gebruik
    -1.35
    ceis
    -1.34
    š
    -1.34
    POSITIVE LOGITS
     for
    1.54
     Y
    1.37
     D
    1.37
     Even
    1.35
     With
    1.34
     V
    1.34
    -
    1.30
     Without
    1.30
     S
    1.29
     To
    1.27
    Activations Density 0.020%

    No Known Activations