© 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. 22-GEMMASCOPE-RES-131K
    4. 73850
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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_22/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
    四个
    -1.13
    简洁
    -1.09
    autorisation
    -1.05
    引用元
    -1.04
     マップ
    -1.02
    𝑝
    -0.99
     zwischen
    -0.98
    Istituto
    -0.96
     πρόσ
    -0.96
    same
    -0.94
    POSITIVE LOGITS
    část
    1.03
    ेटा
    1.01
     letech
    1.00
    0
    1.00
    Nguy
    0.99
    nellement
    0.96
    ेशन
    0.95
     içeris
    0.94
    ified
    0.93
     zowel
    0.93
    Activations Density 0.046%

    No Known Activations