© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128893
    Prev
    Next
    INDEX
    Explanations

    Apache License, Version 2.0

    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
     any
    -0.07
     elves
    -0.06
     многие
    -0.06
     любого
    -0.06
     любы
    -0.06
     interchanges
    -0.06
     вообще
    -0.06
    sticker
    -0.06
     like
    -0.05
     recent
    -0.05
    POSITIVE LOGITS
     firstly
    0.07
     predominantly
    0.06
    Use
    0.06
     Judge
    0.06
     tenter
    0.06
    Firstly
    0.06
    buru
    0.06
     sąd
    0.06
     preliminary
    0.06
     শাসক
    0.06
    Activations Density 0.021%

    No Known Activations