© 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. 322
    Prev
    Next
    INDEX
    Explanations

    governmental and industry entities

    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
     doulou
    -1.19
     for
    -1.17
    nasional
    -1.09
     betek
    -1.02
     šir
    -0.99
     argumento
    -0.96
    біль
    -0.94
    Groet
    -0.93
     más
    -0.93
     morena
    -0.93
    POSITIVE LOGITS
     its
    1.16
     &.
    1.05
     this
    1.04
    Transforms
    1.03
     oll
    1.01
    mathbf
    1.01
     beziehungs
    0.99
     §.
    0.97
     באמצעות
    0.96
    this
    0.95
    Activations Density 0.318%

    No Known Activations