© 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. 41846
    Prev
    Next
    INDEX
    Explanations

    road and railway infrastructure

    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
     الشاشة
    -1.82
    肄
    -1.70
    They
    -1.63
     различни
    -1.61
     Mereka
    -1.59
    yyj
    -1.54
     your
    -1.50
     ихъ
    -1.47
     fühlte
    -1.45
     тях
    -1.42
    POSITIVE LOGITS
     to
    2.22
     so
    1.67
     will
    1.56
     it
    1.48
    έ
    1.41
     would
    1.29
     isn
    1.27
     XIX
    1.21
     finally
    1.16
     VIII
    1.16
    Activations Density 0.183%

    No Known Activations