© 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. 70520
    Prev
    Next
    INDEX
    Explanations

    early January or the

    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
     both
    -1.33
    zków
    -1.24
     sekä
    -1.22
    はもちろん
    -1.20
     sowohl
    -1.16
     nggak
    -1.14
    一方面
    -1.10
     rejects
    -1.09
     many
    -1.09
    Noticias
    -1.09
    POSITIVE LOGITS
     or
    1.48
     более
    1.32
     which
    1.26
     is
    1.19
     других
    1.16
     if
    1.10
     другую
    1.09
     barnen
    1.07
     ebenfalls
    1.06
    
    1.05
    Activations Density 0.235%

    No Known Activations