© 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. 54083
    Prev
    Next
    INDEX
    Explanations

    Kenya National Bureau

    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
     Zelda
    -0.76
     consum
    -0.76
     Canton
    -0.71
     Juin
    -0.69
     Cataluña
    -0.69
     bolts
    -0.69
     Verb
    -0.68
    разви
    -0.68
     transforma
    -0.68
     Mot
    -0.68
    POSITIVE LOGITS
    JspWriter
    0.77
    лив
    0.72
     установка
    0.71
    mashed
    0.70
     Wre
    0.70
     Spre
    0.69
     logements
    0.69
    ุณ
    0.69
     IPR
    0.69
    riere
    0.68
    Activations Density 0.015%

    No Known Activations