© 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. 61240
    Prev
    Next
    INDEX
    Explanations

    plus monetary amounts or items

    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
     which
    -1.52
     sensazione
    -1.33
    1
    -1.31
     américa
    -1.25
     extérieure
    -1.23
     étrangère
    -1.22
     način
    -1.21
    N
    -1.20
     usati
    -1.20
    صیلات
    -1.19
    POSITIVE LOGITS
    mişti
    1.47
     Füßen
    1.44
    Then
    1.38
    ,"
    1.38
     übri
    1.36
     vierte
    1.34
    guigu
    1.34
     elated
    1.31
     inim
    1.31
    ,.
    1.31
    Activations Density 0.016%

    No Known Activations