© 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. 118718
    Prev
    Next
    INDEX
    Explanations

    unique identifiers and IDs

    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
     UUID
    -0.75
    lepší
    -0.74
     vnode
    -0.73
    SpringBoot
    -0.70
    uelto
    -0.69
    ベツ
    -0.69
     honestly
    -0.69
    <?>>
    -0.68
     felt
    -0.68
     frankly
    -0.66
    POSITIVE LOGITS
    Newly
    0.73
     CORE
    0.69
     PHOTOS
    0.68
    ක
    0.68
     Yeni
    0.68
     tiếp
    0.67
     นา
    0.66
     RACE
    0.66
    ág
    0.65
     anew
    0.65
    Activations Density 0.050%

    No Known Activations