© 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. 75192
    Prev
    Next
    INDEX
    Explanations

    acting on

    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
    ’
    -1.84
    ка
    -1.47
     første
    -1.36
     for
    -1.33
     کیا
    -1.33
     lainnya
    -1.29
    的其他
    -1.29
    りました
    -1.29
     other
    -1.28
      
    -1.27
    POSITIVE LOGITS
    它的
    1.70
     internas
    1.69
     Pastikan
    1.68
    他的
    1.60
    郿
    1.54
     décret
    1.52
     abband
    1.50
     faldas
    1.48
    太后
    1.48
     اینکه
    1.47
    Activations Density 0.009%

    No Known Activations