© 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. 103326
    Prev
    Next
    INDEX
    Explanations

    summing up or summarizing

    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
     подроб
    -1.16
     detail
    -1.00
    FULL
    -0.91
    detailed
    -0.90
    釐
    -0.90
     Detail
    -0.88
    也只是
    -0.88
    втор
    -0.87
    oa
    -0.87
    uwen
    -0.86
    POSITIVE LOGITS
     what
    1.66
     everything
    1.29
     all
    1.23
     their
    1.13
     why
    1.13
     succinctly
    1.09
     keseluruhan
    1.08
     neatly
    1.05
     nicely
    1.02
     feelings
    1.01
    Activations Density 0.021%

    No Known Activations