© 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. 10-GEMMASCOPE-RES-131K
    7. 9022
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
    .
    -2.17
        
    -2.05
    л
    -1.88
    -
    -1.80
      
    -1.71
    梣
    -1.69
     别墅
    -1.65
              
    -1.64
    ことがあります
    -1.64
     bepa
    -1.63
    POSITIVE LOGITS
     Saltar
    2.16
     décret
    1.96
     gustado
    1.92
     Therefore
    1.82
    伃
    1.80
     Ayrıca
    1.79
    Additionally
    1.78
    籏
    1.78
    .’
    1.78
    良好的
    1.74
    Activations Density 0.074%

    No Known Activations