© 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. 34-GEMMASCOPE-RES-131K
    7. 103094
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases/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_34/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
     которые
    -1.17
     which
    -1.05
     ktoré
    -1.02
    こともあります
    -1.01
     pág
    -0.99
     perquè
    -0.99
     Turkey
    -0.99
    鯖
    -0.98
    ută
    -0.98
     Turkish
    -0.97
    POSITIVE LOGITS
    踝
    1.48
    Ո
    1.22
    即購入
    1.22
     velik
    1.18
     Nein
    1.16
    Say
    1.16
    četně
    1.16
    Risk
    1.16
    𝐀
    1.16
    THERE
    1.14
    Activations Density 0.002%

    No Known Activations