© 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. 111120
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts

    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
     How
    -1.43
     будет
    -1.41
     mengakui
    -1.39
     spørs
    -1.35
    [
    -1.34
     этого
    -1.34
     "'";
    -1.32
    raujo
    -1.27
     trebuie
    -1.27
     тебя
    -1.27
    POSITIVE LOGITS
     of
    1.78
     także
    1.60
     Ее
    1.52
    stdafx
    1.49
     &
    1.42
    también
    1.41
     גם
    1.38
    ágeno
    1.37
     داریم
    1.36
    必要がある
    1.33
    Activations Density 0.087%

    No Known Activations