© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72167
    Prev
    Next
    INDEX
    Explanations

    schools and internships

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     isInitialized
    -1.19
    atteindre
    -1.08
     posX
    -1.08
     dimentic
    -1.03
     deoarece
    -1.02
     usati
    -1.02
    
    -1.00
    effectuer
    -0.99
    oldt
    -0.99
    proc
    -0.95
    POSITIVE LOGITS
     Choices
    1.16
     bahkan
    1.16
     anche
    1.09
     semua
    1.08
     filós
    1.03
     goddess
    1.02
     backs
    1.02
     نیز
    1.02
     Issues
    1.01
     همه
    1.00
    Activations Density 0.057%

    No Known Activations