© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84859
    Prev
    Next
    INDEX
    Explanations

    web addresses

    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
     vienas
    -1.23
     dificil
    -1.22
     noong
    -1.16
    जब
    -1.16
     alcune
    -1.14
     ぷ
    -1.13
     disponer
    -1.12
     oamen
    -1.10
    recrow
    -1.09
     pagrind
    -1.09
    POSITIVE LOGITS
     at
    7.94
     tại
    2.36
     by
    2.05
     ở
    1.89
     عند
    1.66
    Tại
    1.66
     via
    1.58
     here
    1.54
    At
    1.54
     through
    1.46
    Activations Density 0.111%

    No Known Activations