© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131019
    Prev
    Next
    INDEX
    Explanations

    growth and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hasn
    -0.07
     déjà
    -0.07
     traditionally
    -0.07
    已经
    -0.06
     bislang
    -0.06
     bisher
    -0.06
     historically
    -0.06
    ędzie
    -0.06
     conventionally
    -0.06
     suppresses
    -0.06
    POSITIVE LOGITS
     improvements
    0.06
     broader
    0.06
     verbeter
    0.06
    reas
    0.06
     spreadsheets
    0.05
     ((*
    0.05
    ாலான
    0.05
     improved
    0.05
     sond
    0.05
    рию
    0.05
    Activations Density 0.018%

    No Known Activations