© 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. 115954
    Prev
    Next
    INDEX
    Explanations

    by [name]

    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
     similar
    -0.07
    ),
    -0.06
     ترکیب
    -0.06
    ",
    -0.06
    훤
    -0.06
     Urgent
    -0.06
    éph
    -0.06
     is
    -0.05
     Boy
    -0.05
    豊かな
    -0.05
    POSITIVE LOGITS
     тебя
    0.07
     тебе
    0.06
     тобой
    0.06
     нашей
    0.06
     ٹ
    0.06
     ngươi
    0.06
     आमच्या
    0.06
    estra
    0.05
     Veränder
    0.05
     HeLa
    0.05
    Activations Density 0.010%

    No Known Activations