© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    quoted words

    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
     llenos
    -1.41
    存知
    -1.38
     INFORMACIÓN
    -1.36
    américa
    -1.32
     weißem
    -1.32
    anglicky
    -1.31
    likace
    -1.30
     duradero
    -1.30
     afectados
    -1.29
     Grüßen
    -1.29
    POSITIVE LOGITS
     which
    1.50
     if
    1.49
    ","
    1.39
     this
    1.38
    1.27
    竄
    1.26
    мере
    1.24
    1.23
    ressão
    1.23
    щество
    1.21
    Activations Density 0.069%

    No Known Activations