© 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. 32750
    Prev
    Next
    INDEX
    Explanations

    @ variable names

    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
    Easily
    -1.09
    pasien
    -1.05
    jelaskan
    -1.03
    龇
    -0.96
     Потому
    -0.96
    familie
    -0.95
    easily
    -0.94
    sometimes
    -0.94
    Therefore
    -0.92
    beleid
    -0.92
    POSITIVE LOGITS
     without
    1.37
     additional
    1.36
     before
    1.27
     after
    1.18
     at
    1.09
     another
    1.08
     since
    1.08
     probably
    1.01
     have
    1.00
     ensure
    0.98
    Activations Density 0.005%

    No Known Activations