© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27849
    Prev
    Next
    INDEX
    Explanations

    main menu connection

    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_22/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
    ----</
    -1.24
    '},
    -1.23
     ayudará
    -1.23
    SequentialGroup
    -1.20
     ofrece
    -1.17
     EdgeInsets
    -1.16
    PlayerPrefs
    -1.16
     firmy
    -1.15
    ftar
    -1.14
     Após
    -1.14
    POSITIVE LOGITS
    сторо
    0.98
    O
    0.96
     martens
    0.96
    玉ねぎ
    0.96
             
    0.95
    umb
    0.95
         
    0.95
        
    0.94
      
    0.94
           
    0.94
    Activations Density 0.003%

    No Known Activations