© 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. 128163
    Prev
    Next
    INDEX
    Explanations

    travel experiences

    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
     you
    -0.08
     starts
    -0.07
     начинают
    -0.07
     begins
    -0.07
     will
    -0.07
    如今
    -0.07
     obecnie
    -0.07
    開始
    -0.07
     сейчас
    -0.07
    현재
    -0.07
    POSITIVE LOGITS
    спользова
    0.07
     resultó
    0.06
     actions
    0.06
    多种
    0.06
     diverse
    0.06
     అలాంటి
    0.06
    と思っていた
    0.06
     traditions
    0.06
     polluted
    0.06
     provenant
    0.06
    Activations Density 0.014%

    No Known Activations