© 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. 130499
    Prev
    Next
    INDEX
    Explanations

    multiple or more

    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
      
    -3.22
     generando
    -2.91
     verbess
    -2.70
     sogen
    -2.69
     erweiter
    -2.64
     cambiando
    -2.38
     aumenta
    -2.31
    ing
    -2.31
    to
    -2.31
    惦
    -2.30
    POSITIVE LOGITS
    🢒
    3.05
     pureza
    2.80
     собака
    2.80
     ignite
    2.78
    媜
    2.69
     儿
    2.67
    稣
    2.66
    该如何
    2.63
     humild
    2.63
    jewództ
    2.58
    Activations Density 0.001%

    No Known Activations