© 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. 116091
    Prev
    Next
    INDEX
    Explanations

    after you

    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
    pers
    -0.06
     unremarkable
    -0.06
     overwhelmed
    -0.06
     impractical
    -0.06
     sociais
    -0.06
    得到
    -0.06
     bulunan
    -0.06
    过于
    -0.06
     Dancing
    -0.06
    ॅन
    -0.06
    POSITIVE LOGITS
    ですし
    0.06
     Sebelum
    0.06
     use
    0.06
     other
    0.06
     breadth
    0.06
     Before
    0.06
     контроль
    0.06
    를
    0.06
     다른
    0.05
    Before
    0.05
    Activations Density 0.012%

    No Known Activations