© 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. 22-GEMMASCOPE-RES-131K
    7. 25118
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers followed by codes

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Procu
    -0.96
     コ
    -0.91
    ivez
    -0.89
     Sebelum
    -0.89
     Aseg
    -0.89
     aseg
    -0.87
     beni
    -0.87
     Waktu
    -0.86
    again
    -0.86
     Tanpa
    -0.85
    POSITIVE LOGITS
     and
    0.88
     trám
    0.87
     lác
    0.86
     amongst
    0.85
     respectively
    0.85
    malıdır
    0.85
    čiai
    0.84
     različ
    0.84
    athons
    0.82
     ráp
    0.82
    Activations Density 0.000%

    No Known Activations