© 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. 80828
    Prev
    Next
    INDEX
    Explanations

    top-ranked, top-notch, top-rated

    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
     to
    -2.44
    ↵↵
    -2.20
     —
    -2.03
      
    -2.03
    になっている
    -2.02
     cambiando
    -1.84
    的基本
    -1.79
     folgende
    -1.79
          
    -1.77
    '__
    -1.73
    POSITIVE LOGITS
    最初の
    2.38
    最初に
    2.38
    If
    2.22
    ᠂
    2.16
    涇
    2.05
    Only
    2.03
    浤
    2.03
    必要な
    2.02
    Both
    2.02
    Some
    2.02
    Activations Density 0.003%

    No Known Activations