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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98524
    Prev
    Next
    INDEX
    Explanations

    rows and columns

    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
     only
    -1.34
     even
    -1.05
     now
    -1.03
     people
    -1.00
     still
    -0.99
    Even
    -0.98
     already
    -0.97
     that
    -0.96
     remained
    -0.95
     until
    -0.94
    POSITIVE LOGITS
     dispositifs
    0.99
    哽
    0.97
     colonnes
    0.93
     😁
    0.91
     zoude
    0.89
     ジップ
    0.88
     famoso
    0.86
     usando
    0.86
    izin
    0.85
     étages
    0.84
    Activations Density 0.040%

    No Known Activations