© 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. 47290
    Prev
    Next
    INDEX
    Explanations

    package metadata (author, license, repository)

    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
    王朝
    -0.80
    rektur
    -0.71
     interfer
    -0.71
    onomie
    -0.71
     Hashimoto
    -0.70
     FormData
    -0.70
     comuna
    -0.68
    ubel
    -0.68
     tuber
    -0.66
     AssemblyVersion
    -0.66
    POSITIVE LOGITS
    ('<
    0.75
    arche
    0.72
    DetailView
    0.68
    теро
    0.66
     маски
    0.66
    ัพท์
    0.66
     alternation
    0.65
     Stit
    0.65
    avoir
    0.65
    füh
    0.65
    Activations Density 0.069%

    No Known Activations