© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    generics like <T>

    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
    Not in Any Lists

    No Comments

    Negative Logits
     being
    -1.00
    riebene
    -0.96
     hundreds
    -0.96
     digitalen
    -0.94
     because
    -0.85
     even
    -0.85
     more
    -0.84
    である
    -0.84
    襖
    -0.84
     our
    -0.83
    POSITIVE LOGITS
     T
    0.93
    ())).
    0.88
     anfitrión
    0.88
    なのは
    0.85
     ferocious
    0.85
    T
    0.84
     gruesome
    0.82
     дюй
    0.82
     quirky
    0.82
     azonban
    0.82
    Activations Density 0.013%

    No Known Activations