© 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. 59607
    Prev
    Next
    INDEX
    Explanations

    good news

    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
     your
    -1.93
     a
    -1.59
     where
    -1.55
     consideradas
    -1.55
      
    -1.51
          
    -1.46
    疑问
    -1.45
    疑問
    -1.43
     calentamiento
    -1.42
     ......
    -1.41
    POSITIVE LOGITS
    Ꮨ
    1.68
    之前
    1.61
    providedIn
    1.59
    Of
    1.59
    今回
    1.55
    ą
    1.55
     oogen
    1.53
    第二天
    1.46
    缫
    1.45
     ทั้ง
    1.45
    Activations Density 0.011%

    No Known Activations