© 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. 22-GEMMASCOPE-RES-131K
    7. 11268
    Prev
    Next
    INDEX
    Explanations

    verbs describing outcomes or effects

    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_22/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
     sogenannte
    -1.06
     gegenwär
    -1.00
     sogenannten
    -0.94
    Vidéo
    -0.91
    Musique
    -0.91
     bénévoles
    -0.91
     객체
    -0.90
    自己在
    -0.90
    Notices
    -0.90
    Doge
    -0.90
    POSITIVE LOGITS
     all
    1.11
     this
    1.10
     most
    1.00
     everything
    0.98
    さらに
    0.98
     mostr
    0.98
    Things
    0.97
     milhões
    0.97
    ofus
    0.96
    lograph
    0.96
    Activations Density 0.050%

    No Known Activations