© 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. 128604
    Prev
    Next
    INDEX
    Explanations

    court cases or legal documents

    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
    嵛
    -1.73
    蘩
    -1.67
    leggings
    -1.59
     habang
    -1.59
    "+
    -1.56
    gilet
    -1.55
    Bises
    -1.53
    ׇ
    -1.53
    !»
    -1.51
    ]-->
    -1.51
    POSITIVE LOGITS
     is
    1.78
          
    1.63
           
    1.60
     may
    1.59
     or
    1.59
              
    1.56
         
    1.51
             
    1.41
    探し
    1.41
     häufig
    1.40
    Activations Density 0.000%

    No Known Activations