© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14842
    Prev
    Next
    INDEX
    Explanations

    (code) or ( ) followed by then/and/now

    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
     elevados
    -1.02
     diken
    -0.99
     azeite
    -0.98
     élev
    -0.96
     paillettes
    -0.94
    Northeast
    -0.91
     çay
    -0.90
    potranspiration
    -0.90
     kelle
    -0.89
     banheiro
    -0.89
    POSITIVE LOGITS
     again
    1.39
     then
    1.14
     still
    1.02
     and
    0.99
     whereupon
    0.91
     Again
    0.91
    却
    0.88
    蔔
    0.88
     geko
    0.87
     thereupon
    0.87
    Activations Density 0.015%

    No Known Activations