© 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. 115990
    Prev
    Next
    INDEX
    Explanations

    object properties with counts

    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
     materialize
    -0.07
     getMax
    -0.07
     tweak
    -0.07
     technically
    -0.06
     perishable
    -0.06
     insignia
    -0.06
     lograr
    -0.06
     logo
    -0.06
     כבר
    -0.06
     manifesto
    -0.06
    POSITIVE LOGITS
    እንደ
    0.06
     seperti
    0.06
    我们将
    0.06
     abbiamo
    0.06
    enemies
    0.06
    土地
    0.06
     우리는
    0.06
    Эти
    0.06
     sét
    0.06
     અંગ
    0.06
    Activations Density 0.001%

    No Known Activations