© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128022
    Prev
    Next
    INDEX
    Explanations

    words followed by specific tokens

    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
    Negative Logits
    という
    -0.08
     which
    -0.07
    用于
    -0.07
    など
    -0.07
    たち
    -0.06
     এদের
    -0.06
     に対
    -0.06
     folosit
    -0.06
    なども
    -0.06
     roles
    -0.06
    POSITIVE LOGITS
    佼
    0.06
     you
    0.06
     comprehensive
    0.06
     all
    0.06
     еже
    0.06
    ŧ
    0.06
     самостоятельно
    0.06
    佂
    0.06
     Manufacturers
    0.06
     more
    0.06
    Activations Density 0.002%

    No Known Activations