© 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. 59184
    Prev
    Next
    INDEX
    Explanations

    Broadcom model numbers

    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
     کانال
    -0.78
    értel
    -0.77
     容量
    -0.76
     vnnd
    -0.75
    測定
    -0.74
     channel
    -0.72
    moduleName
    -0.72
     canale
    -0.72
     €)
    -0.72
     Näch
    -0.71
    POSITIVE LOGITS
     ش
    0.78
    Pers
    0.76
    мага
    0.75
    的想法
    0.73
     WAN
    0.70
     чи
    0.69
     Pers
    0.69
     Toro
    0.69
    gle
    0.69
     内
    0.69
    Activations Density 0.020%

    No Known Activations