© 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. 21930
    Prev
    Next
    INDEX
    Explanations

    foreign words and verb phrases

    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
     our
    -1.85
     of
    -1.70
     there
    -1.66
     from
    -1.45
     part
    -1.42
     would
    -1.41
     everyone
    -1.33
     in
    -1.30
     where
    -1.30
     nuestros
    -1.30
    POSITIVE LOGITS
     leurs
    1.49
     adesi
    1.30
    他们的
    1.24
     pengar
    1.23
     papiers
    1.23
     themselves
    1.22
    他们
    1.21
     behar
    1.18
    idk
    1.17
     ۱۸
    1.17
    Activations Density 0.113%

    No Known Activations