© 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. 66386
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

    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
     vulgaires
    -1.58
     kommit
    -1.53
    Every
    -1.51
     """",
    -1.50
     火鍋
    -1.47
    
    -1.47
    Creating
    -1.44
    Those
    -1.43
    Zubereitung
    -1.41
    Usually
    -1.40
    POSITIVE LOGITS
     “
    1.90
    了不少
    1.65
    戗
    1.51
     «
    1.48
     '
    1.41
    了很多
    1.41
     "
    1.40
     mentre
    1.38
     zweimal
    1.35
    了许多
    1.30
    Activations Density 0.005%

    No Known Activations