© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    list of traditions

    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
     and
    -2.42
     during
    -2.02
     first
    -2.02
     for
    -2.00
     epitom
    -1.98
     after
    -1.97
     revital
    -1.97
     through
    -1.96
     helps
    -1.95
     unrelenting
    -1.94
    POSITIVE LOGITS
    ebly
    1.99
    atized
    1.99
     ridiculously
    1.96
    mbal
    1.96
    !!!!!!!
    1.92
    athered
    1.91
    presented
    1.91
     lã
    1.89
    igth
    1.87
    athers
    1.86
    Activations Density 0.022%

    No Known Activations