© 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. 56776
    Prev
    Next
    INDEX
    Explanations

    y starting words

    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
     peck
    -0.73
    гмент
    -0.71
     década
    -0.71
    scala
    -0.69
    izability
    -0.68
     obstinate
    -0.67
     demek
    -0.66
    DHCP
    -0.65
    ♖
    -0.65
     Diakses
    -0.64
    POSITIVE LOGITS
     Yates
    0.95
    ellow
    0.94
    oked
    0.87
     yells
    0.86
     y
    0.85
    ylabel
    0.85
     yelling
    0.85
     yolk
    0.84
     Yum
    0.83
     you
    0.83
    Activations Density 0.028%

    No Known Activations