© 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. 34-GEMMASCOPE-RES-131K
    7. 62606
    Prev
    Next
    INDEX
    Explanations

    Description of the Prior Art

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    opcao
    -0.80
     Xing
    -0.74
    igh
    -0.72
     Euse
    -0.72
     Alice
    -0.68
    Και
    -0.68
     Encoding
    -0.68
     Clerk
    -0.66
    STATIC
    -0.66
    存储
    -0.66
    POSITIVE LOGITS
    Jj
    0.75
    gett
    0.69
    alarme
    0.68
    Gradu
    0.66
    getBean
    0.65
     yonder
    0.65
     dissu
    0.65
    Qq
    0.64
     знамени
    0.64
    Deutsche
    0.63
    Activations Density 0.590%

    No Known Activations