© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27839
    Prev
    Next
    INDEX
    Explanations

    focal medical or programming terms

    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
     there
    -0.99
     encontraban
    -0.95
     our
    -0.93
    റെ
    -0.89
     when
    -0.89
     rodeado
    -0.88
    یین
    -0.83
    婊
    -0.82
    BOTH
    -0.82
     erila
    -0.81
    POSITIVE LOGITS
     laboratorio
    0.94
     และ
    0.88
     secrétaire
    0.85
     Towing
    0.84
    测试
    0.84
     Auditing
    0.83
     confé
    0.83
     Divulgação
    0.82
    และ
    0.82
    
    0.81
    Activations Density 0.734%

    No Known Activations