© 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. 10-GEMMASCOPE-RES-131K
    7. 71111
    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
     you
    -1.66
                  
    -1.56
    postolic
    -1.55
                   
    -1.54
    nemone
    -1.46
                     
    -1.43
                    
    -1.42
     capilar
    -1.41
     your
    -1.41
              
    -1.40
    POSITIVE LOGITS
    4
    2.16
    8
    2.03
    7
    1.92
    5
    1.89
    9
    1.80
    6
    1.63
    3
    1.56
     they
    1.51
     größten
    1.44
     realizó
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.