© 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. 68688
    Prev
    Next
    INDEX
    Explanations

    email citations

    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
     then
    -1.52
    entious
    -1.47
    itizing
    -1.40
     they
    -1.26
    кисло
    -1.21
    Then
    -1.20
    stehen
    -1.18
    ⎔
    -1.17
    itisation
    -1.17
     possib
    -1.15
    POSITIVE LOGITS
     to
    1.59
                
    1.40
     apesar
    1.34
    ?\\
    1.18
     dessas
    1.16
     meski
    1.15
    espn
    1.14
     And
    1.13
                    
    1.13
                   
    1.13
    Activations Density 0.027%

    No Known Activations