© 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. 128114
    Prev
    Next
    INDEX
    Explanations

    patient involvement and autonomy

    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
    An
    -0.06
    Ongoing
    -0.06
    Manip
    -0.06
     Manip
    -0.06
     social
    -0.05
    styling
    -0.05
     போல
    -0.05
     사람
    -0.05
     fert
    -0.05
    zeugen
    -0.05
    POSITIVE LOGITS
     kategori
    0.07
    كاته
    0.06
     रेंज
    0.06
     Selbst
    0.06
     Ult
    0.06
     summer
    0.06
     sous
    0.06
    ämme
    0.06
     geschikt
    0.06
     verantwoord
    0.06
    Activations Density 0.012%

    No Known Activations