© 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. 10314
    Prev
    Next
    INDEX
    Explanations

    how to use

    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
    梣
    -1.77
    _
    -1.76
    ’
    -1.53
     évek
    -1.48
    為了
    -1.48
    重庆
    -1.42
    Buenos
    -1.42
    地區
    -1.41
     diferite
    -1.41
     करने
    -1.41
    POSITIVE LOGITS
     Nichts
    1.80
     Should
    1.61
     Thus
    1.58
     Versuche
    1.55
     to
    1.43
     Again
    1.38
     Usted
    1.36
     You
    1.36
     some
    1.35
     dará
    1.34
    Activations Density 0.041%

    No Known Activations