© 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. 10-GEMMASCOPE-RES-131K
    7. 43398
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     orologio
    -1.49
     Lakukan
    -1.41
    这两个
    -1.39
     compleanno
    -1.38
     таких
    -1.38
     solchen
    -1.38
     takich
    -1.37
     essenziale
    -1.36
    such
    -1.35
     가장
    -1.34
    POSITIVE LOGITS
            
    1.36
     to
    1.35
     Suomen
    1.33
    6
    1.32
    2
    1.30
        
    1.30
     an
    1.30
         
    1.29
    8
    1.23
     -
    1.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.