© 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. 34-GEMMASCOPE-RES-131K
    7. 76503
    Prev
    Next
    INDEX
    Explanations

    every X time unit

    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_34/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
     jednego
    -1.14
    の一つ
    -1.11
     אחד
    -1.10
    หนึ่ง
    -1.02
     واحدة
    -1.00
     אחת
    -1.00
     of
    -0.93
    の一
    -0.93
     более
    -0.93
    之一
    -0.92
    POSITIVE LOGITS
     few
    1.96
     other
    1.91
     two
    1.64
    Other
    1.60
     five
    1.39
    OTHER
    1.39
    Другие
    1.38
     three
    1.38
     Other
    1.28
    few
    1.23
    Activations Density 0.025%

    No Known Activations