© 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. 123725
    Prev
    Next
    INDEX
    Explanations

    Tamil Nadu and Tamil language

    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
     самая
    -1.36
     grandes
    -1.25
     verschiedenen
    -1.24
     a
    -1.23
     parfü
    -1.21
     dirilis
    -1.21
    ="
    -1.20
     darf
    -1.19
     infine
    -1.19
    俢
    -1.16
    POSITIVE LOGITS
     then
    1.45
    ítani
    1.38
    𝑭
    1.38
     necessários
    1.36
    DNN
    1.31
    
    1.30
    phée
    1.28
    Then
    1.27
     than
    1.26
    הם
    1.23
    Activations Density 0.069%

    No Known Activations