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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104061
    Prev
    Next
    INDEX
    Explanations

    Rolling Stone magazine

    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
    那些
    -1.70
    
    -1.65
    訁
    -1.54
      
    -1.52
    czema
    -1.49
                        
    -1.49
     folgendes
    -1.48
     dieselben
    -1.48
    </i>
    -1.46
     gemeinsame
    -1.46
    POSITIVE LOGITS
     for
    1.72
     považ
    1.52
    in
    1.51
     a
    1.50
    man
    1.49
    G
    1.49
     encontraba
    1.46
     four
    1.45
     three
    1.45
     from
    1.41
    Activations Density 0.004%

    No Known Activations