© 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. 22-GEMMASCOPE-RES-131K
    7. 33544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    んですね
    -1.79
    のですね
    -1.60
    のでしょうか
    -1.59
    のですか
    -1.56
    んだろう
    -1.52
    んですよ
    -1.52
    方がいい
    -1.48
    んですよね
    -1.46
     rése
    -1.45
    来週
    -1.45
    POSITIVE LOGITS
             
    1.39
    <bos>
    1.33
           
    1.27
              
    1.20
                  
    1.18
     further
    1.17
    だが
    1.16
    ですが
    1.15
     also
    1.14
    だから
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.