© 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. 11977
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and concepts

    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
     that
    -2.06
     as
    -2.06
     For
    -1.87
     their
    -1.86
     While
    -1.84
     while
    -1.80
        
    -1.74
      
    -1.74
     regarding
    -1.72
    見て
    -1.72
    POSITIVE LOGITS
    
    2.14
     ชิ้น
    2.08
     個室
    2.05
    栳
    1.98
    six
    1.98
    琤
    1.98
    甶
    1.97
    aneers
    1.97
    cation
    1.95
    four
    1.91
    Activations Density 0.004%

    No Known Activations