© 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. 68744
    Prev
    Next
    INDEX
    Explanations

    mono, swift, assemblies, cli

    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
     that
    -1.40
     same
    -1.40
    怍
    -1.29
     finding
    -1.29
     haces
    -1.23
     uñas
    -1.21
     parques
    -1.20
    ↵↵
    -1.20
     people
    -1.19
     między
    -1.19
    POSITIVE LOGITS
    '
    1.40
    гмент
    1.24
    вини
    1.24
    ’
    1.23
     proble
    1.20
    où
    1.20
    gül
    1.20
    rowData
    1.18
    amá
    1.17
     Praze
    1.17
    Activations Density 0.045%

    No Known Activations