© 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. 32939
    Prev
    Next
    INDEX
    Explanations

    legal citations ending in period

    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
    Not in Any Lists

    No Comments

    Negative Logits
     all
    -1.36
     if
    -1.27
     in
    -1.16
     now
    -1.14
     you
    -1.14
     most
    -1.13
     are
    -1.08
     that
    -1.05
     on
    -1.04
     і
    -1.04
    POSITIVE LOGITS
     genoux
    1.18
     gede
    1.07
     vorige
    1.03
    Ŗ
    1.02
     jambes
    1.02
     oídos
    1.00
    ஏ
    0.99
     Hooks
    0.99
     meningkatkan
    0.98
    łop
    0.98
    Activations Density 0.004%

    No Known Activations