© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49683
    Prev
    Next
    INDEX
    Explanations

    data types and sizes

    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
    编号
    -0.83
     院
    -0.79
     بيها
    -0.74
    munk
    -0.72
     pregunt
    -0.71
    繊
    -0.70
     levan
    -0.69
    แจ
    -0.69
    лич
    -0.68
     printers
    -0.68
    POSITIVE LOGITS
     word
    2.70
     words
    2.53
    word
    2.27
    Word
    2.22
    Words
    2.17
     Words
    2.16
    words
    2.13
     Word
    2.03
     WORD
    1.76
     WORDS
    1.71
    Activations Density 0.051%

    No Known Activations