© 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. 94263
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix word construction

    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
    出来ない
    -1.13
    Lij
    -1.06
    できません
    -1.05
     in
    -1.02
    corollary
    -1.00
    Hij
    -0.99
    Jep
    -0.99
    cadi
    -0.97
    immen
    -0.97
    TRIBUN
    -0.96
    POSITIVE LOGITS
    itizing
    1.15
     dente
    1.15
     foro
    1.14
    ervant
    1.14
    tront
    1.13
    .\
    1.13
    imetry
    1.10
     éx
    1.09
    ization
    1.09
    ara
    1.08
    Activations Density 0.240%

    No Known Activations