© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123820
    Prev
    Next
    INDEX
    Explanations

    buy, obtain, download, watch, purchase

    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
     verstanden
    -1.48
    はじめまして
    -1.48
     каждый
    -1.34
     zawsze
    -1.34
     asegur
    -1.33
     its
    -1.27
     your
    -1.27
     naszych
    -1.27
    本日は
    -1.25
     nasz
    -1.22
    POSITIVE LOGITS
     for
    1.78
     on
    1.51
     उन्होंने
    1.32
     through
    1.27
     via
    1.24
     They
    1.24
     mereka
    1.23
     their
    1.23
     themselves
    1.22
     now
    1.21
    Activations Density 0.143%

    No Known Activations