© 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. 105996
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     i
    -1.55
     and
    -1.35
     but
    -1.27
     sadece
    -1.21
     beschreibt
    -1.16
    湳
    -1.16
     entstanden
    -1.15
     today
    -1.15
    such
    -1.13
     influencing
    -1.13
    POSITIVE LOGITS
    桖
    1.38
     görmek
    1.34
    rógeno
    1.30
    话说
    1.29
     garçon
    1.29
     dasselbe
    1.27
    Пусть
    1.23
    Oleh
    1.20
    hoka
    1.18
     玛
    1.18
    Activations Density 0.015%

    No Known Activations