© 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. 127862
    Prev
    Next
    INDEX
    Explanations

    code in various languages

    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
     our
    -0.96
    careous
    -0.94
     mög
    -0.88
     Bereichen
    -0.86
    辞典
    -0.85
     Bakterien
    -0.85
     kesalahan
    -0.83
    álni
    -0.82
     niega
    -0.82
    iseerd
    -0.82
    POSITIVE LOGITS
    different
    1.02
     Prin
    0.94
    arsh
    0.92
     komis
    0.90
    مانی
    0.89
     persecu
    0.88
    excellent
    0.86
     frustra
    0.86
    lader
    0.85
     gustos
    0.85
    Activations Density 0.005%

    No Known Activations