© 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. 115840
    Prev
    Next
    INDEX
    Explanations

    introductions and headings

    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
     criada
    -0.07
     predomin
    -0.07
     между
    -0.06
    gående
    -0.06
     encontrada
    -0.06
     crankshaft
    -0.06
    ్రహ్
    -0.06
     produzione
    -0.06
     रिएक्टर
    -0.06
     Raw
    -0.06
    POSITIVE LOGITS
     upon
    0.08
     tablecloth
    0.06
    culpa
    0.06
     عفوا
    0.06
    neutral
    0.05
     lors
    0.05
    berry
    0.05
     एल्गोरि
    0.05
    ghost
    0.05
     센
    0.05
    Activations Density 0.005%

    No Known Activations