© 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. 115973
    Prev
    Next
    INDEX
    Explanations

    video media player

    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
     allows
    -0.07
     offers
    -0.07
     disenfranch
    -0.06
     there
    -0.06
     provides
    -0.06
     服务
    -0.06
    ELIST
    -0.06
     wants
    -0.06
     can
    -0.06
     serves
    -0.06
    POSITIVE LOGITS
     こと
    0.06
     goto
    0.06
     зимой
    0.06
    輝
    0.06
    userid
    0.06
     Algeria
    0.05
     применение
    0.05
    करना
    0.05
    )».
    0.05
     ultim
    0.05
    Activations Density 0.003%

    No Known Activations