© 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. 90768
    Prev
    Next
    INDEX
    Explanations

    technical jargon and abbreviations

    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
    Bolivia
    -0.77
    Folks
    -0.77
     ligger
    -0.74
    形状
    -0.73
     обеспечить
    -0.73
     Hadley
    -0.71
     admissible
    -0.71
    біль
    -0.69
     jälkeen
    -0.69
     funcionario
    -0.69
    POSITIVE LOGITS
     Minneapolis
    0.88
    Assembler
    0.85
     Hor
    0.79
    stages
    0.79
    Minneapolis
    0.77
    須賀
    0.76
    angolo
    0.75
     издание
    0.74
    fka
    0.73
    звание
    0.73
    Activations Density 0.019%

    No Known Activations