© 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. 83884
    Prev
    Next
    INDEX
    Explanations

    pay per, fee for, buy one

    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
    Surprisingly
    -2.05
     new
    -1.66
     после
    -1.62
    }
    -1.58
    aneity
    -1.54
     >
    -1.49
     would
    -1.48
     Surprisingly
    -1.47
    teness
    -1.46
    romycin
    -1.43
    POSITIVE LOGITS
    ,
    1.61
     testé
    1.53
     réellement
    1.51
     abordagem
    1.49
    kijk
    1.46
     deportistas
    1.39
     impresionantes
    1.36
     gardes
    1.34
     árvore
    1.34
     informação
    1.34
    Activations Density 0.044%

    No Known Activations