© 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. 34-GEMMASCOPE-RES-131K
    7. 118537
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     even
    -1.09
      
    -1.06
     after
    -1.05
     can
    -1.04
     huge
    -1.01
     really
    -0.98
     dabar
    -0.98
     usually
    -0.97
       
    -0.93
     in
    -0.91
    POSITIVE LOGITS
     dormitórios
    1.07
     қара
    1.03
     inasmuch
    1.03
    certainly
    1.02
     cetera
    1.01
     Bengaluru
    0.98
    ClCompile
    0.95
    MLLoader
    0.95
    ḿ
    0.93
     『
    0.93
    Activations Density 0.067%

    No Known Activations