© 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. 6697
    Prev
    Next
    INDEX
    Explanations

    moving, processing, storing

    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
     Collect
    -1.23
     Collecting
    -1.16
     collecting
    -1.15
     retrieve
    -1.13
    Collect
    -1.13
     retrieving
    -1.13
    收集
    -1.12
     collect
    -1.11
     retrieved
    -1.10
     collects
    -1.09
    POSITIVE LOGITS
     then
    1.48
     resell
    1.32
     placed
    1.15
     stored
    1.12
    放到
    1.06
     put
    1.06
     used
    1.03
     resold
    1.03
     processed
    1.01
    Then
    1.00
    Activations Density 0.144%

    No Known Activations