© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32574
    Prev
    Next
    INDEX
    Explanations

    international words or code

    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
    Negative Logits
    mariage
    -1.23
     today
    -1.20
    antastic
    -1.16
    razer
    -1.16
    isst
    -1.13
    igenous
    -1.12
     olvidado
    -1.08
    loed
    -1.08
    naval
    -1.06
     either
    -1.05
    POSITIVE LOGITS
    שלום
    1.19
    เคย
    1.18
    asy
    1.07
    ⁦
    1.06
     ही
    1.06
    Основ
    1.00
    А
    0.99
     paragraphe
    0.98
    История
    0.98
     inicio
    0.98
    Activations Density 0.002%

    No Known Activations