© 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. 34575
    Prev
    Next
    INDEX
    Explanations

    computer memory types DDR DRAM

    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
    baarheid
    -0.82
    рила
    -0.77
    onacci
    -0.76
    unicip
    -0.75
    离婚
    -0.75
    Tina
    -0.74
    belajaran
    -0.73
     piatto
    -0.73
     ruk
    -0.73
     持つ
    -0.73
    POSITIVE LOGITS
     DDR
    1.65
    DDR
    1.34
     SDR
    1.29
     memory
    1.05
     RAM
    1.00
     GD
    0.97
    SDR
    0.96
    ddr
    0.88
     ddr
    0.88
     faster
    0.84
    Activations Density 0.048%

    No Known Activations