© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14130
    Prev
    Next
    INDEX
    Explanations

    pre-treatment or preparation

    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
     derzeit
    -1.63
      
    -1.46
     aproximada
    -1.39
     atualmente
    -1.38
    为什么会
    -1.36
     current
    -1.35
     erstmals
    -1.34
     począ
    -1.34
    楽しみです
    -1.34
     regresar
    -1.33
    POSITIVE LOGITS
    媜
    1.73
    Ранее
    1.58
    
    1.55
    سوال
    1.48
     Ahead
    1.48
    ahead
    1.45
    beforeEach
    1.45
    ÍTULO
    1.44
    Подготовка
    1.41
    Количество
    1.30
    Activations Density 0.256%

    No Known Activations