© 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. 127905
    Prev
    Next
    INDEX
    Explanations

    timestamp markers

    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
     that
    -2.03
     this
    -1.52
     even
    -1.38
     immediately
    -1.27
     today
    -1.25
     until
    -1.09
     during
    -1.05
     of
    -1.04
     especially
    -1.03
     wanted
    -1.02
    POSITIVE LOGITS
    🦠
    1.08
     douleurs
    1.05
    médiaire
    1.05
    реи
    1.05
    ifikasi
    1.03
    izient
    0.99
     récol
    0.97
    ногда
    0.97
    gebnisse
    0.97
     bakter
    0.97
    Activations Density 0.023%

    No Known Activations