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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78926
    Prev
    Next
    INDEX
    Explanations

    text following certain words

    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_34/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
    いい
    -1.27
    ’
    -1.18
      
    -1.18
    [
    -1.03
        
    -0.98
    ↵↵
    -0.97
    (
    -0.94
    いても
    -0.94
       
    -0.93
         
    -0.92
    POSITIVE LOGITS
    ually
    1.88
    ual
    1.58
    ured
    1.33
     снимки
    1.25
     podoba
    1.18
     Wahrheit
    1.13
    boxes
    1.12
    urized
    1.11
    ract
    1.10
    ualmente
    1.10
    Activations Density 0.054%

    No Known Activations