© 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. 10-GEMMASCOPE-RES-131K
    7. 65135
    Prev
    Next
    INDEX
    Explanations

    explaining with that

    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_10/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
     a
    -2.16
     it
    -1.66
     time
    -1.62
     era
    -1.58
    那就
    -1.56
     an
    -1.54
          
    -1.46
     ,
    -1.42
     E
    -1.41
    -1.40
    POSITIVE LOGITS
    越來
    1.66
     empêche
    1.65
     GONNA
    1.61
     Commencez
    1.57
     Pristup
    1.55
    endida
    1.55
     levier
    1.50
    Zubereitung
    1.49
     with
    1.48
    AHUL
    1.48
    Activations Density 0.050%

    No Known Activations