© 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. 117467
    Prev
    Next
    INDEX
    Explanations

    race and identity

    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
    Not in Any Lists

    No Comments

    Negative Logits
    potential
    -0.07
     potensi
    -0.07
     Potential
    -0.06
     موجوده
    -0.06
     potential
    -0.06
    Potential
    -0.06
     altamente
    -0.06
     данни
    -0.06
     área
    -0.06
    highest
    -0.06
    POSITIVE LOGITS
     false
    0.06
     مذ
    0.06
    nobody
    0.06
     sarkar
    0.06
     sert
    0.06
     gpointer
    0.06
    ڄ
    0.06
     नवी
    0.06
    Shane
    0.06
    fisherman
    0.06
    Activations Density 0.038%

    No Known Activations