© 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. 127849
    Prev
    Next
    INDEX
    Explanations

    França, null, new, lion, Prince

    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
     禁止
    -0.99
    是怎么回事
    -0.98
    Preparación
    -0.94
    哪怕
    -0.91
    MAKING
    -0.91
    即便是
    -0.91
    即便
    -0.91
    with
    -0.90
     letzten
    -0.90
    w
    -0.90
    POSITIVE LOGITS
    França
    1.08
    aspectj
    1.02
     ['$
    1.02
    وقال
    1.01
    getUserName
    0.98
    由于
    0.98
    咖啡
    0.97
    Πηγές
    0.97
    เพราะ
    0.97
    ḩ
    0.97
    Activations Density 0.045%

    No Known Activations