© 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. 128100
    Prev
    Next
    INDEX
    Explanations

    self base `saved`InstanceState `jsp`

    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
     আৰ
    -0.07
     kadang
    -0.07
     иногда
    -0.06
     sometimes
    -0.06
     گاه
    -0.06
     photons
    -0.06
    Sometimes
    -0.06
    ហើយ
    -0.06
     called
    -0.06
    有时
    -0.06
    POSITIVE LOGITS
     what
    0.07
     соответствии
    0.06
     accordance
    0.06
    ⅱ
    0.06
     his
    0.06
    asmuch
    0.06
     Nokia
    0.06
    喽
    0.06
     yêu
    0.06
     IKEA
    0.06
    Activations Density 0.016%

    No Known Activations