© 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. 58368
    Prev
    Next
    INDEX
    Explanations

    physical objects and components

    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
    Not in Any Lists

    No Comments

    Negative Logits
     своей
    -1.13
    ListGroup
    -1.12
         
    -1.11
     viņ
    -1.10
                  
    -1.10
          
    -1.07
     but
    -1.06
     prior
    -1.06
     elettron
    -1.05
     ``
    -1.04
    POSITIVE LOGITS
    ladas
    1.26
     tromper
    1.09
    kové
    1.08
    ことです
    1.06
     Перейти
    1.05
    nikom
    1.05
     sayuran
    1.05
    อาจ
    1.04
     may
    1.03
    ();*/
    1.02
    Activations Density 0.588%

    No Known Activations