© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70654
    Prev
    Next
    INDEX
    Explanations

    pioneering new or first efforts

    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
     najwięks
    -1.82
    """
    -1.63
     støtte
    -1.58
     duże
    -1.56
       
    -1.55
    ↵↵
    -1.52
      
    -1.49
     począ
    -1.48
     maravillas
    -1.42
    .
    -1.40
    POSITIVE LOGITS
     如果
    1.89
    quelize
    1.85
    udades
    1.78
     of
    1.77
    jmniej
    1.72
    遢
    1.71
     как
    1.69
    賒
    1.64
    Kontrola
    1.64
    匐
    1.63
    Activations Density 0.007%

    No Known Activations