© 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. 128117
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

    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
     યોગ
    -0.06
     buvo
    -0.06
     February
    -0.06
     solar
    -0.06
     terhadap
    -0.06
    短い
    -0.06
     announce
    -0.06
     அமை
    -0.06
     announcing
    -0.06
     лютого
    -0.06
    POSITIVE LOGITS
    Undo
    0.06
    他在
    0.06
    他是
    0.06
     পরিষদে
    0.06
     negozio
    0.06
     dirinya
    0.06
    eed
    0.06
    在他的
    0.06
    他的
    0.05
     hänen
    0.05
    Activations Density 0.001%

    No Known Activations